# imgnAI Katana API

Complete Integration Guide for LLMs

This document is designed for an LLM or coding agent that has never heard of imgnAI before. It explains what the service is, how to authenticate or pay with x402, how to submit image, video, and text/LLM requests, how to attach images, how to obey model-specific media rules, and which model names/aspects/costs are available.

The documentation site's full-catalog `Copy for LLMs` button copies this same `/llms.txt` content. Use this file as the canonical full integration context for LLMs and coding agents.

imgnAI's API is the paid production gateway for generating images, videos, and text/LLM completions from prompts, optional image references, optional video frame inputs, optional audio references, and multimodal chat messages on the models that support them. The service accepts JSON requests over HTTP. Image and video generation uses `/v1/generation-requests`. Text models use the OpenAI-compatible `/v1/chat/completions` endpoint. Paid generation endpoints can be called with either an imgnAI API key/credit balance or x402 USDC payment.

## Service URLs and Account Setup

- Base URL for this deployment: `http://devkat.imgnai.com`
- imgnAI web app: https://app.imgnai.com
- Buy credits and subscriptions: https://app.imgnai.com
- Get an API key: https://app.imgnai.com/api
- Create or view existing API keys: https://app.imgnai.com/api
- Reference price used for rough USD estimates: $0.0047 per credit, based on Platinum Annual pricing.

## Authentication and x402 Payment

Standard account billing uses API key headers. Do not place these credentials in the JSON body.

```http
X-API-Key: <api_key>
X-API-Secret: <secret_key>
```

Text/OpenAI-compatible clients may use one combined bearer token:

```http
Authorization: Bearer <api_key>:<api_secret>
```

Anonymous paid calls use x402 instead of API keys. x402 follows the HTTP 402 flow: first call the endpoint without credentials, receive a `402 Payment Required` response, build and sign one of the returned USDC payment options, then retry the exact same request with the Base64 JSON payment payload in the `PAYMENT-SIGNATURE` header. imgnAI only starts processing after the x402 payment is verified and settled.

x402 headers:

```http
PAYMENT-REQUIRED: <base64 JSON payment requirements returned by imgnAI>
PAYMENT-SIGNATURE: <base64 JSON signed x402 payment sent by the client>
PAYMENT-RESPONSE: <base64 JSON settlement receipt returned by imgnAI>
```

x402 details:

- x402 version: `2`.
- Payment scheme: `exact`.
- Currency: USDC, atomic units with 6 decimals.
- Supported networks: Base (`eip155:8453`) and Solana (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`).
- Base is listed first and should be the default client choice.
- The returned `accepts` entries include `scheme`, `network`, `asset`, `payTo`, `amount`, `maxAmountRequired`, `maxTimeoutSeconds`, and explanatory `extra` metadata.
- Gas is estimated by imgnAI and charged in USDC as part of the x402 amount. This covers the oracle/facilitator settlement transaction cost on Base or Solana.
- Image/video x402 prices use the model's USDC price metadata. Text x402 prices are prepaid from the reserve estimate because final token usage is only known after inference.
- The server generates the canonical `request_id` after payment and returns it in the successful response. `client_request_id` is optional and never required.
- For async image/video x402 calls, use the returned `request_id` to poll `GET /v1/generation-requests/{request_id}`. The request id is unguessable; no API key is required for x402 polling.

x402 discovery endpoint:

```http
GET /v1/x402
```

x402 image/video discovery call:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true' \
  -H 'Content-Type: application/json' \
  -d '{"requests":[{"type":"image","model":"gen","prompt":"A clean product photo of a mug","aspect_ratio":"1:1","output_format":"png"}]}'
```

The response status will be `402`. Decode `PAYMENT-REQUIRED` as Base64 JSON, choose an `accepts` item, sign/pay it using an x402-compatible client, then retry:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>' \
  -d '<same JSON body as the discovery call>'
```

x402 text/LLM calls use the same flow against `/v1/chat/completions`; omit `Authorization`, receive `402`, then retry with `PAYMENT-SIGNATURE`.

## x402 Zero-Context Integration Guide

This section assumes the reader has no previous context about imgnAI or x402. x402 is an HTTP-native payment flow for paid API requests. The client first sends the ordinary API request without an API key. imgnAI replies with HTTP `402 Payment Required` and a `PAYMENT-REQUIRED` response header. That header is Base64-encoded JSON containing exact USDC payment instructions. The client signs or constructs one of the returned payment options, retries the exact same HTTP request with `PAYMENT-SIGNATURE`, and imgnAI verifies and settles payment before starting image, video, or text inference.

The same x402 flow works for:

- Image and video generation: `POST http://devkat.imgnai.com/v1/generation-requests?wait=true`
- Text/LLM chat completions: `POST http://devkat.imgnai.com/v1/chat/completions`
- Capability discovery: `GET http://devkat.imgnai.com/v1/x402`

Do not send `X-API-Key`, `X-API-Secret`, or `Authorization` when using x402. The payment itself authorizes that one request. imgnAI generates the canonical `request_id`; clients may send `client_request_id` as an optional debugging or idempotency label, but it is not required and is not the canonical server id.

Gas is included in the USDC amount. imgnAI estimates the Base or Solana settlement gas/network fee, converts that estimate to USDC, adds a safety markup, and includes it in `amount` / `maxAmountRequired`. The user pays a single exact USDC amount. imgnAI pays the actual settlement gas from the oracle/facilitator wallet, so the service does not start work until the payment covers both the model price and the estimated settlement cost. For Solana, if the imgnAI payTo associated token account does not exist yet, the quoted gas also includes the rent/setup cost needed to create it.

### x402 request sequence

1. Build the normal JSON body for the image, video, or text request.
2. Send it without API credentials and without `PAYMENT-SIGNATURE`.
3. Expect HTTP `402 Payment Required`.
4. Read `PAYMENT-REQUIRED`. Decode it as Base64, then parse the decoded UTF-8 string as JSON.
5. Read `accepts`. Each entry is one supported payment option. imgnAI returns Base USDC first and Solana USDC second.
6. Choose exactly one `accepts` entry. Do not edit the amount, recipient, asset, network, or timeout.
7. Build the network-specific payment payload for that exact `accepts` entry.
8. Base64-encode the payment payload JSON.
9. Retry the exact same endpoint, method, query string, and JSON body with `PAYMENT-SIGNATURE: <base64-json-payment>`.
10. If payment verifies and settles, imgnAI starts inference and returns the normal API response. Successful responses include `PAYMENT-RESPONSE`, a Base64 JSON settlement receipt.

### PAYMENT-REQUIRED shape

The decoded requirement is a JSON object similar to:

```json
{
  "x402Version": 2,
  "error": "Payment required",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "asset": "0xBASE_USDC_CONTRACT",
      "payTo": "0xIMGNAI_BASE_ORACLE",
      "amount": "13938",
      "maxAmountRequired": "13938",
      "maxTimeoutSeconds": 120,
      "extra": {
        "asset_decimals": 6,
        "asset_symbol": "USDC",
        "breakdown": {
          "service_usdc": "0.010000",
          "gas_usdc": "0.003938",
          "total_usdc": "0.013938"
        }
      }
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "payTo": "IMGNAI_SOLANA_ORACLE_PUBKEY",
      "amount": "11500",
      "maxAmountRequired": "11500",
      "maxTimeoutSeconds": 120
    }
  ]
}
```

All USDC values are atomic units with 6 decimals. For example, `"13938"` means `0.013938` USDC.

### Base x402 payment payload

Base uses network `eip155:8453`. imgnAI expects USDC payment using a signed EIP-3009-style `transferWithAuthorization` authorization. This is the smooth USDC flow where the payer signs typed data and imgnAI submits the transfer onchain from its oracle wallet.

To build the Base signature:

- Use the exact Base `accepts` entry returned in `PAYMENT-REQUIRED`.
- Use the payer wallet address as `authorization.from`.
- Use `accept.payTo` as `authorization.to`.
- Use `accept.amount` as `authorization.value`.
- Set `validAfter` to the current Unix timestamp or `0`.
- Set `validBefore` before `accept.maxTimeoutSeconds` expires.
- Generate a fresh 32-byte random `nonce` for every payment. Do not reuse it.
- Sign EIP-712 typed data for USDC `TransferWithAuthorization`.
- Domain: `name: "USD Coin"`, `version: "2"`, `chainId: 8453`, `verifyingContract: accept.asset`.
- Primary type: `TransferWithAuthorization`.
- Fields: `from`, `to`, `value`, `validAfter`, `validBefore`, `nonce`.

Base payment payload JSON before Base64 encoding:

```json
{
  "x402Version": 2,
  "accepted": {
    "scheme": "exact",
    "network": "eip155:8453",
    "asset": "0xBASE_USDC_CONTRACT",
    "payTo": "0xIMGNAI_BASE_ORACLE",
    "amount": "13938",
    "maxAmountRequired": "13938",
    "maxTimeoutSeconds": 120
  },
  "payload": {
    "authorization": {
      "from": "0xPAYER_WALLET",
      "to": "0xIMGNAI_BASE_ORACLE",
      "value": "13938",
      "validAfter": 1778430000,
      "validBefore": 1778430120,
      "nonce": "0x32_BYTES_RANDOM_HEX"
    },
    "signature": "0xEIP712_SIGNATURE"
  }
}
```

PAYMENT-SIGNATURE for Base is:

```text
base64(json_utf8_string_of_the_payload_above)
```

Base retry example:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-base-transferwithauthorization-payment>' \
  -d '{"requests":[{"type":"image","model":"gen","prompt":"A precise studio image of a brushed steel cube","aspect_ratio":"1:1","output_format":"png"}]}'
```

### Solana x402 payment payload

Solana uses network `solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp` and native Solana USDC mint `EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v`. imgnAI expects a serialized VersionedTransaction that transfers the exact USDC amount from the payer's associated token account to the imgnAI oracle/payTo associated token account.

To build the Solana transaction:

- Use the exact Solana `accepts` entry returned in `PAYMENT-REQUIRED`.
- The USDC mint must be `accept.asset`.
- The token recipient owner must be `accept.payTo`.
- The token amount must equal `accept.amount` exactly.
- The transaction fee payer must be the imgnAI oracle/payTo public key. imgnAI co-signs the fee payer after validating the transfer.
- The customer signs as the USDC token owner. imgnAI will reject transactions that do not contain the required customer token-owner signature.
- If the recipient associated token account does not exist, include the associated-token-account creation instruction with the oracle/payTo as fee payer.
- Use a recent blockhash. If a public RPC reports `BlockhashNotFound`, rebuild and re-sign with a fresh finalized blockhash.
- Serialize the complete VersionedTransaction bytes and encode those bytes as Base64.

Solana payment payload JSON before Base64 encoding:

```json
{
  "x402Version": 2,
  "accepted": {
    "scheme": "exact",
    "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
    "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
    "payTo": "IMGNAI_SOLANA_ORACLE_PUBKEY",
    "amount": "11500",
    "maxAmountRequired": "11500",
    "maxTimeoutSeconds": 120
  },
  "payload": {
    "payer": "CUSTOMER_SOLANA_WALLET",
    "transaction": "<base64-serialized-VersionedTransaction>"
  }
}
```

PAYMENT-SIGNATURE for Solana is:

```text
base64(json_utf8_string_of_the_payload_above)
```

Solana retry example:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-solana-serialized-transaction-payment>' \
  -d '{"requests":[{"type":"image","model":"gen","prompt":"A precise studio image of a brushed steel cube","aspect_ratio":"1:1","output_format":"png"}]}'
```

### Text x402 example

Text x402 uses the same 402 discovery and paid retry flow as image/video. The only difference is the endpoint and body shape. Text calls are prepaid from a reserve estimate because the final prompt/completion token usage is only known after the model returns.

Discovery:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -d '{"model":"claude-haiku-4-5","messages":[{"role":"user","content":"Reply with exactly: text x402 ok"}],"max_tokens":16}'
```

Paid retry on Base or Solana:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-payment-for-selected-network>' \
  -d '{"model":"claude-haiku-4-5","messages":[{"role":"user","content":"Reply with exactly: text x402 ok"}],"max_tokens":16}'
```

### Video x402 example

Video x402 uses `/v1/generation-requests` and the ordinary video request body. Model media rules still apply, so do not mix first-frame/last-frame/reference/audio slots in combinations rejected by the selected video model.

Discovery:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true&wait_timeout_seconds=120' \
  -H 'Content-Type: application/json' \
  -d '{"requests":[{"type":"video","model":"seedance-2-0-fast","prompt":"A five second smooth dolly shot of a glass sculpture on a table","duration_seconds":5,"aspect_ratio":"16:9"}]}'
```

Paid retry on Base or Solana:

```bash
curl -i -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true&wait_timeout_seconds=120' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-payment-for-selected-network>' \
  -d '{"requests":[{"type":"video","model":"seedance-2-0-fast","prompt":"A five second smooth dolly shot of a glass sculpture on a table","duration_seconds":5,"aspect_ratio":"16:9"}]}'
```

### x402 implementation notes for agents

- Decode `PAYMENT-REQUIRED` from the response header, not from scraped HTML.
- Preserve the exact request body between the unpaid discovery call and the paid retry.
- Use the returned amount from the selected `accepts` entry. Never hard-code prices from examples.
- Choose Base by default if the user does not request a network, because it is listed first.
- Choose Solana when the user wants to pay from a Solana wallet or when a Solana x402 client is already available.
- A 402 response with `PAYMENT-REQUIRED` means no inference work has started yet.
- A successful paid response includes `PAYMENT-RESPONSE`; decode it for settlement metadata such as transaction hash/signature, network, and paid amount.
- Image/video responses may be asynchronous. If the returned status is `accepted` or `processing`, poll `GET /v1/generation-requests/{request_id}` until completion.
- x402 payments are one-request payments. Do not reuse a Base nonce or Solana transaction for another request.
- If a payment is invalid, expired, for the wrong amount, wrong recipient, wrong asset, or wrong network, imgnAI returns a 402-style payment error and does not start inference.

## Main Generation Endpoint

Submit generation jobs to:

```http
POST /v1/generation-requests?wait=true&wait_timeout_seconds=60
```

Use `wait=true` when you want the HTTP response to wait briefly for outputs. Use `wait=false` for asynchronous behavior, then poll:

```http
GET /v1/generation-requests/{request_id}
```

The top-level request body is always a JSON object with:

- `client_request_id`: optional caller-defined idempotency/debug identifier.
- `requests`: array of generation items. Each item is either `type: "image"` or `type: "video"`.

Do not send a caller-defined request id. imgnAI generates and returns `request_id`. `client_request_id` is optional. Use top-level `output_format` for image output format; do not send an `output` object for ordinary integrations.

## Text / LLM Chat Completion Basics

Text models are exposed through an OpenAI-compatible chat completions endpoint. Existing OpenAI SDK integrations can point their base URL at this service and use a single combined bearer credential in the form `<api_key>:<api_secret>`.

```http
POST /v1/chat/completions
Authorization: Bearer <api_key>:<api_secret>
Content-Type: application/json
```

Minimal text chat example:

```json
{
  "model": "grok-4-3",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

Compatibility notes:

- Preferred request shape is OpenAI-style `messages`. For clients that send a single string `prompt`, the API converts it into one user message when `messages` is omitted.
- `stream: true` is supported with Server-Sent Events. The API forwards chunks as `data: ...`, rewrites the chunk model name to the public imgnAI model name, requests usage in the final stream chunk, then finalizes billing before `data: [DONE]`.
- If a streaming provider does not return usage in the stream, imgnAI keeps the pre-charge reserve instead of refunding based on an unknown cost. Set `max_tokens` or `max_completion_tokens` to keep the reserve predictable.

Streaming text chat example:

```json
{
  "model": "grok-4-3",
  "messages": [
    {
      "role": "user",
      "content": "Write one concise sentence about API integration."
    }
  ],
  "max_tokens": 128,
  "stream": true,
  "stream_options": {
    "include_usage": true
  }
}
```

Vision chat example with a Base64 data URL. The API accepts HTTPS image URLs, full `data:image/...;base64,...` data URLs, or raw base64 image strings in `image_url.url`. Base64 image inputs are converted to JPEG, capped to a maximum side of 4096px, and kept at the original aspect ratio before inference.

```json
{
  "model": "grok-4-3",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe this image for an accessibility caption."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,<BASE64_ENCODED_IMAGE_BYTES>"
          }
        }
      ]
    }
  ],
  "max_tokens": 256
}
```

Text billing rules:

- Text models are charged from actual provider usage after the response returns, using prompt/input tokens and completion/output tokens.
- Published token prices include imgnAI's 10% service markup and are shown in credits using the Platinum Annual reference price.
- Every call has a minimum final charge of 0.1 credits and is rounded up to the nearest 0.1 credit.
- The API pre-charges a reserve before dispatch so users cannot consume compute they cannot pay for. The normal minimum reserve is 10 credits; requests with a large `max_tokens` or `max_completion_tokens` can reserve more.
- After the provider returns usage, the API refunds the difference if the final cost is lower than the reserve. If a request exceeds the reserve, it charges the overage before recording final usage.
- If neither `max_tokens` nor `max_completion_tokens` is supplied and the selected model supports output caps, the API applies a conservative default cap so the reserve is meaningful.
- The response includes `usage.imgnai` with credits reserved, credits charged, credits refunded, billed USD estimate, privacy mode, public model name, and `billing_source`.

Text privacy labels:

- `Anonymized`: customer account identity is not sent with the inference request. The model operator may process prompt content.
- `E2EE Private`: the request is routed through hardware-protected confidential computing. Private model metadata lists Intel TDX and NVIDIA Confidential Computing where applicable, and these models expose privacy proof metadata through `/v1/text/attestation` where supported.
- Public imgnAI docs intentionally do not expose the internal inference provider used for a given text model.

Privacy proof example for private text models:

```bash
curl 'http://devkat.imgnai.com/v1/text/attestation?model=kimi-k2-6-private&nonce=<64_hex_nonce>' \
  -H 'Authorization: Bearer <api_key>:<api_secret>'
```

## Image Generation Basics

Image generation items use `type: "image"`. Required fields are normally `model`, `prompt`, and `aspect_ratio`. Some edit/reference models also accept input images. Use the public model name listed in this document, not the internal backend model name.

Minimal text-to-image example:

```json
{
  "client_request_id": "client-example",
  "requests": [
    {
      "id": "image-1",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

Image edit/reference example with HTTPS image URLs:

```json
{
  "client_request_id": "client-image-reference-example",
  "requests": [
    {
      "id": "image-reference-1",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "Use the reference image as the product and place it on a clean studio table with soft daylight.",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/reference-image.png"
      ]
    }
  ]
}
```

Image edit/reference example with Base64 data URLs:

```json
{
  "client_request_id": "client-image-reference-example",
  "requests": [
    {
      "id": "image-reference-1",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "Use the reference image as the product and place it on a clean studio table with soft daylight.",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "data:image/png;base64,<BASE64_ENCODED_IMAGE_BYTES>"
      ]
    }
  ]
}
```

Image `reference_assets` example. `reference_assets` is useful when you want to label uploaded images by role. For image models, accepted image-like asset kinds include `source_image`, `image`, `mask`, `style_reference`, and `start_frame`. Each asset may provide `url` or `base64_data`.

```json
{
  "client_request_id": "client-image-reference-assets-example",
  "requests": [
    {
      "id": "image-assets-1",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "Create a polished product ad using the source product and the style reference.",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "reference_assets": [
        {
          "kind": "source_image",
          "url": "https://example.com/product.png"
        },
        {
          "kind": "style_reference",
          "base64_data": "data:image/jpeg;base64,<BASE64_ENCODED_STYLE_REFERENCE>"
        }
      ]
    }
  ]
}
```

Image attachment rules:

- `image_urls` is the preferred compatibility field for source/reference images. `input_images` and `input_image_urls` are accepted aliases.
- `image_urls`, `input_images`, and `input_image_urls` may be a list of HTTPS URLs, data URLs, or raw base64 strings.
- `image_url`, `input_image_url`, `input_image`, and `input_image_b64` may provide a single source image.
- Data URL format should look like `data:image/png;base64,<BASE64_BYTES>` or `data:image/jpeg;base64,<BASE64_BYTES>`.
- Raw base64 image strings are also accepted; the API wraps them as image data internally.
- Corrupt or unreadable base64 image data is rejected before dispatch.
- `aspect_ratio` accepts strings such as `1:1`, `16:9`, `9:16`, and `21:9`; `aspect_ratio: "auto"` inspects the first image input and chooses the closest model-supported ratio. If no image is supplied, AUTO defaults to `1:1` when the selected model supports it.
- `output_format` accepts `png`, `jpeg`, or `webp`. `jpg` is accepted as an alias for `jpeg`.
- Use only aspect ratios listed for the selected model. External API models often support a smaller aspect set than imgnAI-hosted models.
- On imgnAI-hosted image models only, `is_fast`/`fast_mode` request lower-cost half-resolution generation and `is_uhd`/`uhd_mode` request UHD generation. `is_uhd` takes precedence when both are sent.
- On supported tag/booru-based image models only, prompt assist fields such as `use_assistant`, `prompt_assist`, or `use_prompt_assist` let users write natural language that is translated to tag-style prompts before dispatch.

## Video Generation Basics

Video generation items use `type: "video"`. Required fields are normally `model`, `prompt`, `duration_seconds`, and `aspect_ratio`. Media inputs go in `video_image_data`; older compatibility fields such as `image_url` or `input_image_url` can map to first-frame image input, but new integrations should prefer `video_image_data`.

Minimal text-to-video example:

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "video-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

Video with first-frame image URL:

```json
{
  "client_request_id": "client-video-first-frame-example",
  "requests": [
    {
      "id": "video-first-frame-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Animate the scene from the first frame with a slow cinematic camera push and natural motion.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

Video with first-frame Base64 data URL:

```json
{
  "client_request_id": "client-video-first-frame-example",
  "requests": [
    {
      "id": "video-first-frame-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Animate the scene from the first frame with a slow cinematic camera push and natural motion.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "data:image/png;base64,<BASE64_ENCODED_FIRST_FRAME>"
      }
    }
  ]
}
```

Video with first frame and last frame, for models where `supports_first_frame` and `supports_last_frame` are both true:

```json
{
  "client_request_id": "client-video-first-last-frame-example",
  "requests": [
    {
      "id": "video-first-last-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Create a smooth transformation from the first frame to the last frame with consistent subject identity.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "last_frame_image_url": "https://example.com/last-frame.png"
      }
    }
  ]
}
```

Video with reference images, for models where `supports_reference_images` is true:

```json
{
  "client_request_id": "client-video-reference-images-example",
  "requests": [
    {
      "id": "video-references-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Create a video using the uploaded references for subject identity, wardrobe, and setting.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/character-reference.png",
          "data:image/png;base64,<BASE64_ENCODED_PROP_REFERENCE>"
        ]
      }
    }
  ]
}
```

Video with reference image assets, using `reference_assets` instead of directly writing `video_image_data.reference_image_urls`:

```json
{
  "client_request_id": "client-video-reference-assets-example",
  "requests": [
    {
      "id": "video-reference-assets-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Generate a short ad using the character reference and the environment reference.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/person.png"
        },
        {
          "kind": "image",
          "base64_data": "data:image/png;base64,<BASE64_ENCODED_ENVIRONMENT>"
        }
      ]
    }
  ]
}
```

Video with audio references, for models where `supports_audio_input` is true:

```json
{
  "client_request_id": "client-video-audio-reference-example",
  "requests": [
    {
      "id": "video-audio-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Create a cinematic video and use the attached audio as the voice or sound reference.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/speaker-reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-voice.mp3"
        ]
      }
    }
  ]
}
```

## Complete HTTP cURL Examples

Text-to-image cURL example:

```bash
curl -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true&wait_timeout_seconds=60' \
  -H 'Content-Type: application/json' \
  -H 'X-API-Key: <api_key>' \
  -H 'X-API-Secret: <secret_key>' \
  -d '{
  "client_request_id": "client-image-reference-example",
  "requests": [
    {
      "id": "image-reference-1",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "Use the reference image as the product and place it on a clean studio table with soft daylight.",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/reference-image.png"
      ]
    }
  ]
}'
```

Video with reference images cURL example:

```bash
curl -X POST 'http://devkat.imgnai.com/v1/generation-requests?wait=true&wait_timeout_seconds=120' \
  -H 'Content-Type: application/json' \
  -H 'X-API-Key: <api_key>' \
  -H 'X-API-Secret: <secret_key>' \
  -d '{
  "client_request_id": "client-video-reference-images-example",
  "requests": [
    {
      "id": "video-references-1",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "Create a video using the uploaded references for subject identity, wardrobe, and setting.",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/character-reference.png",
          "data:image/png;base64,<BASE64_ENCODED_PROP_REFERENCE>"
        ]
      }
    }
  ]
}'
```

Base64 note for curl examples: replace placeholders such as `data:image/png;base64,<BASE64_ENCODED_IMAGE_BYTES>` with a real data URL. If creating the request from a local file, read the bytes, base64 encode them, and prefix with the correct media type, for example `data:image/png;base64,`.

Video media input rules:

- Put video media inputs in `video_image_data`.
- `video_image_data.first_frame_image_url`: first/source frame image. Accepted values are HTTPS URL, data URL, or raw base64 image string. Top-level `image_url`, `input_image_url`, `input_image`, and `input_image_b64` are accepted compatibility aliases for this slot.
- `video_image_data.mid_frame_image_url`: mid-frame image, only if the model supports mid-frame input.
- `video_image_data.last_frame_image_url`: last/end frame image, only if the model supports last-frame input.
- `video_image_data.reference_image_urls`: array of reference images, only if the model supports reference images. Top-level `reference_image_urls` is accepted as a compatibility alias. Obey `maximum_reference_images`.
- `video_image_data.audio_input_urls`: array of audio reference URLs, only if the model supports audio input. Obey `maximum_reference_audio_files` and the global cap of 4.
- `reference_assets` can also provide media. Image kinds `style_reference`, `reference_image`, and `image` map to video reference images. Audio kinds `audio`, `source_audio`, `reference_audio`, and `audio_reference` map to audio reference inputs.
- Do not send audio references to models where `supports_audio_input` is false. The API rejects unsupported audio input before dispatch.
- Do not mix first/last frame inputs with reference images unless the selected model's custom rules allow that combination.
- Use only durations listed in `video_lengths_and_costs` for the selected model.
- Use only aspect ratios listed in `supported_aspects` for the selected model. `aspect_ratio: "auto"` uses the first frame first, then the first reference image. If neither exists, AUTO defaults to `1:1` when supported by the selected model.
- `audio_gen_model: false` means the generated video is silent/no-audio. Most modern video models generate audio by default, so this document calls out silent models as the exception.

## Video Custom Rule Glossary

Always inspect each selected video model's `custom_rules` before composing a request. These rules are model-specific compatibility constraints enforced by the API before dispatch.

- `audio_15s_max`: Combined selected audio input is limited to 15 seconds. Keep audio references short.
- `audio_drives_duration`: The requested video duration follows the selected audio duration. Prefer matching the prompt and expected motion to the audio clip.
- `audio_ff_only`: Audio input can only be used with first-frame conditioning. Do not combine audio input with mid-frame, last-frame, or reference-image conditioning.
- `audio_needs_reference_image`: Audio input requires at least one reference image.
- `audio_or_fflf_exclusive`: Audio input cannot be combined with first-frame or last-frame inputs. Choose audio conditioning or frame conditioning.
- `lf_needs_ff`: A last-frame image requires a first-frame image. Do not send a last frame by itself.
- `reference_ff_only`: Reference images may be combined with first-frame input, but not with last-frame input.
- `reference_is_voice_timbre`: When reference images are present, reference audio is interpreted as voice timbre rather than a full audio track.
- `reference_no_ff_or_lf`: Reference images cannot be combined with first-frame or last-frame inputs. Use either reference images, or first/last frame conditioning, but not both.

## Common Failure Cases and How to Avoid Them

- Unsupported aspect ratio: choose a value from the selected model's supported aspect list.
- Unsupported duration: choose one of the selected video model's `video_lengths_and_costs` keys.
- Corrupt base64 image: validate that the data decodes to an actual image before submitting.
- Audio reference on unsupported model: only send `audio_input_urls` when `supports_audio_input` is true.
- Reference images mixed with first/last frame on incompatible video model: check `custom_rules`, especially `reference_no_ff_or_lf`.
- Last frame without first frame: prohibited on models with `lf_needs_ff`.
- Too many reference images: clamp to `multi_image_inputs_allowed` for image models or `maximum_reference_images` for video models.

## Model Selection Checklist for an LLM

1. Decide whether the user needs text, an image, or a video.
2. For text, use `/v1/chat/completions`; for image/video, use `/v1/generation-requests`.
3. Pick a model whose public model name, supported input types/aspects, privacy mode, and media capabilities match the requested workflow.
4. Use the public model name shown as `Model name to send`.
5. For image/video, choose an allowed `aspect_ratio`.
6. For video, choose an allowed `duration_seconds`.
7. Add only media fields supported by that model.
8. Apply every listed `custom_rule` for video models.
9. If using local image files, convert them to data URLs (`data:image/...;base64,...`) before sending.
10. Submit text to `/v1/chat/completions`; submit image/video to `/v1/generation-requests?wait=true` or submit async and poll the request id.

## Text Models

### Grok 4.3 (`grok-4-3`)

- Model name to send: `grok-4-3`
- Publisher: xAI
- Release date: 2026-04-30
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: not listed
- Supported input types: text, image
- Cost: 292.6 credits / 1M input tokens (US$1.38); 585.2 credits / 1M output tokens (US$2.75)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 292.6 credits per 1M input tokens.
- Output price: 585.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

### Qwen3.6 35B A3B (`qwen3-6-35b-a3b`)

- Model name to send: `qwen3-6-35b-a3b`
- Publisher: Qwen
- Release date: 2026-04-27
- Privacy: Anonymized
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text, image, video
- Cost: 35.2 credits / 1M input tokens (US$0.1650); 234.1 credits / 1M output tokens (US$1.10)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 35.2 credits per 1M input tokens.
- Output price: 234.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Video input, Tool calling, Structured output, Long context
- Description: Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

### Qwen3.6 Flash (`qwen3-6-flash`)

- Model name to send: `qwen3-6-flash`
- Publisher: Qwen
- Release date: 2026-04-27
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: 65536
- Supported input types: text, image, video
- Cost: 58.6 credits / 1M input tokens (US$0.2750); 351.1 credits / 1M output tokens (US$1.65)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 58.6 credits per 1M input tokens.
- Output price: 351.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Video input, Tool calling, Structured output, Long context
- Description: Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...

### Qwen3.6 Max Preview (`qwen3-6-max-preview`)

- Model name to send: `qwen3-6-max-preview`
- Publisher: Qwen
- Release date: 2026-04-27
- Privacy: Anonymized
- Context length: 262144 tokens
- Max output tokens: 65536
- Supported input types: text
- Cost: 243.5 credits / 1M input tokens (US$1.14); 1460.5 credits / 1M output tokens (US$6.86)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 243.5 credits per 1M input tokens.
- Output price: 1460.5 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...

### DeepSeek V4 Flash (`deepseek-v4-flash`)

- Model name to send: `deepseek-v4-flash`
- Publisher: DeepSeek
- Release date: 2026-04-24
- Privacy: Anonymized
- Context length: 1048576 tokens
- Max output tokens: 384000
- Supported input types: text
- Cost: 32.8 credits / 1M input tokens (US$0.1540); 65.6 credits / 1M output tokens (US$0.3080)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 32.8 credits per 1M input tokens.
- Output price: 65.6 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

### DeepSeek V4 Pro (`deepseek-v4-pro`)

- Model name to send: `deepseek-v4-pro`
- Publisher: DeepSeek
- Release date: 2026-04-24
- Privacy: Anonymized
- Context length: 1048576 tokens
- Max output tokens: 384000
- Supported input types: text
- Cost: 101.9 credits / 1M input tokens (US$0.4785); 203.7 credits / 1M output tokens (US$0.9570)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 101.9 credits per 1M input tokens.
- Output price: 203.7 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

### GPT-5.5 (`gpt-5-5`)

- Model name to send: `gpt-5-5`
- Publisher: OpenAI
- Release date: 2026-04-24
- Privacy: Anonymized
- Context length: 1050000 tokens
- Max output tokens: 128000
- Supported input types: file, image, text
- Cost: 1170.3 credits / 1M input tokens (US$5.50); 7021.3 credits / 1M output tokens (US$33.00)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 1170.3 credits per 1M input tokens.
- Output price: 7021.3 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Tool calling, Structured output, Long context
- Description: GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

### Kimi K2.6 Private (`kimi-k2-6-private`)

- Model name to send: `kimi-k2-6-private`
- Publisher: MoonshotAI
- Release date: 2026-04-21
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text, image
- Cost: 255.2 credits / 1M input tokens (US$1.20); 1076.6 credits / 1M output tokens (US$5.06)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 255.2 credits per 1M input tokens.
- Output price: 1076.6 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Tool calling, Structured output, Long context
- Description: Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and demonstrates strong performance in agentic workflows.

### Qwen3 Coder Next Private (`qwen3-coder-next-private`)

- Model name to send: `qwen3-coder-next-private`
- Publisher: Qwen
- Release date: 2026-04-21
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text
- Cost: 42.2 credits / 1M input tokens (US$0.1980); 280.9 credits / 1M output tokens (US$1.32)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 42.2 credits per 1M input tokens.
- Output price: 280.9 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output, Long context
- Description: Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering competitive performance with efficient inference.

### GLM 5.1 Private (`glm-5-1-private`)

- Model name to send: `glm-5-1-private`
- Publisher: Z.ai
- Release date: 2026-04-20
- Privacy: E2EE Private
- Context length: 202752 tokens
- Max output tokens: 202752
- Supported input types: text
- Cost: 283.2 credits / 1M input tokens (US$1.33); 983.0 credits / 1M output tokens (US$4.62)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 283.2 credits per 1M input tokens.
- Output price: 983.0 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output, Long context
- Description: GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

### Kimi K2.6 (`kimi-k2-6`)

- Model name to send: `kimi-k2-6`
- Publisher: MoonshotAI
- Release date: 2026-04-20
- Privacy: Anonymized
- Context length: 262144 tokens
- Max output tokens: 16384
- Supported input types: text, image
- Cost: 175.6 credits / 1M input tokens (US$0.8250); 819.2 credits / 1M output tokens (US$3.85)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 175.6 credits per 1M input tokens.
- Output price: 819.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

### MiMo-V2-Flash Private (`mimo-v2-flash-private`)

- Model name to send: `mimo-v2-flash-private`
- Publisher: Xiaomi
- Release date: 2026-04-20
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text
- Cost: 23.5 credits / 1M input tokens (US$0.1100); 70.3 credits / 1M output tokens (US$0.3300)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 23.5 credits per 1M input tokens.
- Output price: 70.3 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output, Long context
- Description: MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a...

### Claude Opus 4.7 (`claude-opus-4-7`)

- Model name to send: `claude-opus-4-7`
- Publisher: Anthropic
- Release date: 2026-04-16
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: 128000
- Supported input types: text, image
- Cost: 1170.3 credits / 1M input tokens (US$5.50); 5851.1 credits / 1M output tokens (US$27.50)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 1170.3 credits per 1M input tokens.
- Output price: 5851.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

### GLM 5.1 (`glm-5-1`)

- Model name to send: `glm-5-1`
- Publisher: Z.ai
- Release date: 2026-04-07
- Privacy: Anonymized
- Context length: 202752 tokens
- Max output tokens: 65535
- Supported input types: text
- Cost: 245.8 credits / 1M input tokens (US$1.16); 819.2 credits / 1M output tokens (US$3.85)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 245.8 credits per 1M input tokens.
- Output price: 819.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

### Gemma 4 26B A4B (`gemma-4-26b-a4b`)

- Model name to send: `gemma-4-26b-a4b`
- Publisher: Google
- Release date: 2026-04-03
- Privacy: Anonymized
- Context length: 262144 tokens
- Max output tokens: not listed
- Supported input types: image, text, video
- Cost: 14.1 credits / 1M input tokens (US$0.0660); 77.3 credits / 1M output tokens (US$0.3630)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 14.1 credits per 1M input tokens.
- Output price: 77.3 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Video input, Tool calling, Structured output, Long context
- Description: Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

### Gemma 4 31B (`gemma-4-31b`)

- Model name to send: `gemma-4-31b`
- Publisher: Google
- Release date: 2026-04-02
- Privacy: Anonymized
- Context length: 262144 tokens
- Max output tokens: 16384
- Supported input types: image, text, video
- Cost: 30.5 credits / 1M input tokens (US$0.1430); 89.0 credits / 1M output tokens (US$0.4180)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 30.5 credits per 1M input tokens.
- Output price: 89.0 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Video input, Tool calling, Structured output, Long context
- Description: Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

### Qwen3.6 Plus (`qwen3-6-plus`)

- Model name to send: `qwen3-6-plus`
- Publisher: Qwen
- Release date: 2026-04-02
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: 65536
- Supported input types: text, image, video
- Cost: 76.1 credits / 1M input tokens (US$0.3575); 456.4 credits / 1M output tokens (US$2.15)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 76.1 credits per 1M input tokens.
- Output price: 456.4 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Video input, Tool calling, Structured output, Long context
- Description: Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

### Grok 4.20 (`grok-4-20`)

- Model name to send: `grok-4-20`
- Publisher: xAI
- Release date: 2026-03-31
- Privacy: Anonymized
- Context length: 2000000 tokens
- Max output tokens: not listed
- Supported input types: text, image, file
- Cost: 292.6 credits / 1M input tokens (US$1.38); 585.2 credits / 1M output tokens (US$2.75)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 292.6 credits per 1M input tokens.
- Output price: 585.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Tool calling, Structured output, Long context
- Description: Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

### Grok 4.20 Multi-Agent (`grok-4-20-multi-agent`)

- Model name to send: `grok-4-20-multi-agent`
- Publisher: xAI
- Release date: 2026-03-31
- Privacy: Anonymized
- Context length: 2000000 tokens
- Max output tokens: not listed
- Supported input types: text, image, file
- Cost: 468.1 credits / 1M input tokens (US$2.20); 1404.3 credits / 1M output tokens (US$6.60)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 468.1 credits per 1M input tokens.
- Output price: 1404.3 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Structured output, Long context
- Description: Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...

### MiniMax M2.7 (`minimax-m2-7`)

- Model name to send: `minimax-m2-7`
- Publisher: MiniMax
- Release date: 2026-03-18
- Privacy: Anonymized
- Context length: 196608 tokens
- Max output tokens: 131072
- Supported input types: text
- Cost: 70.0 credits / 1M input tokens (US$0.3289); 280.9 credits / 1M output tokens (US$1.32)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 70.0 credits per 1M input tokens.
- Output price: 280.9 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output
- Description: MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

### GPT-5.4 Mini (`gpt-5-4-mini`)

- Model name to send: `gpt-5-4-mini`
- Publisher: OpenAI
- Release date: 2026-03-17
- Privacy: Anonymized
- Context length: 400000 tokens
- Max output tokens: 128000
- Supported input types: file, image, text
- Cost: 175.6 credits / 1M input tokens (US$0.8250); 1053.2 credits / 1M output tokens (US$4.95)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 175.6 credits per 1M input tokens.
- Output price: 1053.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Tool calling, Structured output, Long context
- Description: GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

### GLM 5 Turbo (`glm-5-turbo`)

- Model name to send: `glm-5-turbo`
- Publisher: Z.ai
- Release date: 2026-03-15
- Privacy: Anonymized
- Context length: 202752 tokens
- Max output tokens: 131072
- Supported input types: text
- Cost: 280.9 credits / 1M input tokens (US$1.32); 936.2 credits / 1M output tokens (US$4.40)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 280.9 credits per 1M input tokens.
- Output price: 936.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

### Qwen3.5-27B Private (`qwen3-5-27b-private`)

- Model name to send: `qwen3-5-27b-private`
- Publisher: Qwen
- Release date: 2026-03-13
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text, image, video
- Cost: 70.3 credits / 1M input tokens (US$0.3300); 561.8 credits / 1M output tokens (US$2.64)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 70.3 credits per 1M input tokens.
- Output price: 561.8 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Video input, Tool calling, Structured output, Long context
- Description: The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.

### GPT-5.4 (`gpt-5-4`)

- Model name to send: `gpt-5-4`
- Publisher: OpenAI
- Release date: 2026-03-05
- Privacy: Anonymized
- Context length: 1050000 tokens
- Max output tokens: 128000
- Supported input types: text, image, file
- Cost: 585.2 credits / 1M input tokens (US$2.75); 3510.7 credits / 1M output tokens (US$16.50)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 585.2 credits per 1M input tokens.
- Output price: 3510.7 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Tool calling, Structured output, Long context
- Description: GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

### Gemini 3.1 Flash Lite Preview (`gemini-3-1-flash-lite-preview`)

- Model name to send: `gemini-3-1-flash-lite-preview`
- Publisher: Google
- Release date: 2026-03-03
- Privacy: Anonymized
- Context length: 1048576 tokens
- Max output tokens: 65536
- Supported input types: text, image, video, file, audio
- Cost: 58.6 credits / 1M input tokens (US$0.2750); 351.1 credits / 1M output tokens (US$1.65)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 58.6 credits per 1M input tokens.
- Output price: 351.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context
- Description: Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

### Qwen3.5 397B A17B Private (`qwen3-5-397b-a17b-private`)

- Model name to send: `qwen3-5-397b-a17b-private`
- Publisher: Qwen
- Release date: 2026-02-28
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text, image, video
- Cost: 128.8 credits / 1M input tokens (US$0.6050); 819.2 credits / 1M output tokens (US$3.85)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 128.8 credits per 1M input tokens.
- Output price: 819.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Video input, Tool calling, Structured output, Long context
- Description: The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.

### MiniMax M2.5 Private (`minimax-m2-5-private`)

- Model name to send: `minimax-m2-5-private`
- Publisher: MiniMax
- Release date: 2026-02-21
- Privacy: E2EE Private
- Context length: 196608 tokens
- Max output tokens: 196608
- Supported input types: text
- Cost: 46.9 credits / 1M input tokens (US$0.2200); 323.0 credits / 1M output tokens (US$1.52)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 46.9 credits per 1M input tokens.
- Output price: 323.0 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output
- Description: MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

### Gemini 3.1 Pro Preview (`gemini-3-1-pro-preview`)

- Model name to send: `gemini-3-1-pro-preview`
- Publisher: Google
- Release date: 2026-02-19
- Privacy: Anonymized
- Context length: 1048576 tokens
- Max output tokens: 65536
- Supported input types: audio, file, image, text, video
- Cost: 468.1 credits / 1M input tokens (US$2.20); 2808.6 credits / 1M output tokens (US$13.20)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 468.1 credits per 1M input tokens.
- Output price: 2808.6 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context
- Description: Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

### Claude Sonnet 4.6 (`claude-sonnet-4-6`)

- Model name to send: `claude-sonnet-4-6`
- Publisher: Anthropic
- Release date: 2026-02-17
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: 128000
- Supported input types: text, image
- Cost: 702.2 credits / 1M input tokens (US$3.30); 3510.7 credits / 1M output tokens (US$16.50)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 702.2 credits per 1M input tokens.
- Output price: 3510.7 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

### GLM 5 (`glm-5`)

- Model name to send: `glm-5`
- Publisher: Z.ai
- Release date: 2026-02-11
- Privacy: Anonymized
- Context length: 202752 tokens
- Max output tokens: not listed
- Supported input types: text
- Cost: 140.5 credits / 1M input tokens (US$0.6600); 449.4 credits / 1M output tokens (US$2.11)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 140.5 credits per 1M input tokens.
- Output price: 449.4 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Tool calling, Structured output, Long context
- Description: GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

### GLM 5 Private (`glm-5-private`)

- Model name to send: `glm-5-private`
- Publisher: Z.ai
- Release date: 2026-02-10
- Privacy: E2EE Private
- Context length: 202752 tokens
- Max output tokens: 202752
- Supported input types: text
- Cost: 280.9 credits / 1M input tokens (US$1.32); 819.2 credits / 1M output tokens (US$3.85)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 280.9 credits per 1M input tokens.
- Output price: 819.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output, Long context
- Description: GLM-5 is an open-source foundation model built for complex systems engineering and long-horizon agent workflows. It delivers production-grade productivity for large-scale programming tasks, with performance aligned to top closed-source models, and is designed for expert developers building at the system level.

### Claude Opus 4.6 (`claude-opus-4-6`)

- Model name to send: `claude-opus-4-6`
- Publisher: Anthropic
- Release date: 2026-02-04
- Privacy: Anonymized
- Context length: 1000000 tokens
- Max output tokens: 128000
- Supported input types: text, image
- Cost: 1170.3 credits / 1M input tokens (US$5.50); 5851.1 credits / 1M output tokens (US$27.50)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 1170.3 credits per 1M input tokens.
- Output price: 5851.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

### Kimi K2.5 Private (`kimi-k2-5-private`)

- Model name to send: `kimi-k2-5-private`
- Publisher: MoonshotAI
- Release date: 2026-01-29
- Privacy: E2EE Private
- Context length: 262144 tokens
- Max output tokens: 262144
- Supported input types: text, image
- Cost: 140.5 credits / 1M input tokens (US$0.6600); 702.2 credits / 1M output tokens (US$3.30)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 140.5 credits per 1M input tokens.
- Output price: 702.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Tool calling, Structured output, Long context
- Description: Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

### Gemini 3 Flash Preview (`gemini-3-flash-preview`)

- Model name to send: `gemini-3-flash-preview`
- Publisher: Google
- Release date: 2025-12-17
- Privacy: Anonymized
- Context length: 1048576 tokens
- Max output tokens: 65536
- Supported input types: text, image, file, audio, video
- Cost: 117.1 credits / 1M input tokens (US$0.5500); 702.2 credits / 1M output tokens (US$3.30)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 117.1 credits per 1M input tokens.
- Output price: 702.2 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context
- Description: Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

### DeepSeek V3.2 Private (`deepseek-v3-2-private`)

- Model name to send: `deepseek-v3-2-private`
- Publisher: DeepSeek
- Release date: 2025-12-03
- Privacy: E2EE Private
- Context length: 163840 tokens
- Max output tokens: 163840
- Supported input types: text
- Cost: 74.9 credits / 1M input tokens (US$0.3520); 112.4 credits / 1M output tokens (US$0.5280)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 74.9 credits per 1M input tokens.
- Output price: 112.4 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Tool calling, Structured output
- Description: DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

### Qwen3 Coder 480B A35B Private (`qwen3-coder-480b-a35b-private`)

- Model name to send: `qwen3-coder-480b-a35b-private`
- Publisher: Qwen
- Release date: 2025-11-28
- Privacy: E2EE Private
- Context length: 262000 tokens
- Max output tokens: 262000
- Supported input types: text
- Cost: 468.1 credits / 1M input tokens (US$2.20); 468.1 credits / 1M output tokens (US$2.20)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 468.1 credits per 1M input tokens.
- Output price: 468.1 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Long context
- Description: Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).

### Qwen3 VL 30B A3B Instruct Private (`qwen3-vl-30b-a3b-instruct-private`)

- Model name to send: `qwen3-vl-30b-a3b-instruct-private`
- Publisher: Qwen
- Release date: 2025-11-28
- Privacy: E2EE Private
- Context length: 128000 tokens
- Max output tokens: 128000
- Supported input types: text, image
- Cost: 46.9 credits / 1M input tokens (US$0.2200); 163.9 credits / 1M output tokens (US$0.7700)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 46.9 credits per 1M input tokens.
- Output price: 163.9 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Tool calling, Structured output
- Description: Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.

### Claude Haiku 4.5 (`claude-haiku-4-5`)

- Model name to send: `claude-haiku-4-5`
- Publisher: Anthropic
- Release date: 2025-10-15
- Privacy: Anonymized
- Context length: 200000 tokens
- Max output tokens: 64000
- Supported input types: image, text
- Cost: 234.1 credits / 1M input tokens (US$1.10); 1170.3 credits / 1M output tokens (US$5.50)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 234.1 credits per 1M input tokens.
- Output price: 1170.3 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: Anonymized, Vision, Tool calling, Structured output, Long context
- Description: Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

### Gemma 3 27B Private (`gemma-3-27b-private`)

- Model name to send: `gemma-3-27b-private`
- Publisher: Google
- Release date: 2025-10-03
- Privacy: E2EE Private
- Context length: 53920 tokens
- Max output tokens: 53920
- Supported input types: text, image
- Cost: 25.8 credits / 1M input tokens (US$0.1210); 93.7 credits / 1M output tokens (US$0.4400)
- x402: supported. Call without Authorization to receive a 402 payment requirement, then retry with PAYMENT-SIGNATURE. Text x402 calls are prepaid from the reserve estimate because final token usage is only known after inference.
- Input price: 25.8 credits per 1M input tokens.
- Output price: 93.7 credits per 1M output tokens.
- Billing: pre-charge reserve, then refund or charge the difference from actual token usage. Minimum final charge is 0.1 credits, rounded up to the nearest 0.1 credit.
- Features: E2EE Private, Vision, Tool calling, Structured output
- Description: Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)


## Image Models

### GPT Image 2 (`gpt-image-2`)

- Model name to send: `gpt-image-2`
- Creator: OpenAI
- Cost: 14 credits per image (~$0.0658)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 16
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/gptimage2.webp
- Description: OpenAI's latest and greatest Image Generation & Editing model, delivering a massive leap forward in prompt adherence, stylistic control, and text rendering!

### Nano Banana 2 (`nano-banana-2`)

- Model name to send: `nano-banana-2`
- Creator: Google
- Cost: 32 credits per image (~$0.1504)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 14
- Supported aspects: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/nanobanana2.webp
- Description: Google's frontier image creation and edit model, showcasing unprecedented quality and prompt adherence, along with in-built full web search capabilities!

### Gen (`gen`)

- Model name to send: `gen`
- Creator: imgnAI
- Cost: 3 credits per image (~$0.0141)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/flux1x.webp
- Description: Our flexible, general-purpose model for any style or subject.

### Seedream 5.0 Lite (`seedream-5-0-lite`)

- Model name to send: `seedream-5-0-lite`
- Creator: ByteDance
- Cost: 7 credits per image (~$0.0329)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 10
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/seedream5lite.webp
- Description: ByteDance's lightweight, next-gen Image model - with full edit and reference capabilities!

### WAN 2.7 Image Pro (`wan-2-7-image-pro`)

- Model name to send: `wan-2-7-image-pro`
- Creator: Alibaba
- Cost: 14 credits per image (~$0.0658)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 9
- Supported aspects: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/wan27proimage.webp
- Description: Alibaba's WAN 2.7 Image Pro model, merging true-to-life realism with full reference & edit capabilities.

### Ani (`ani`)

- Model name to send: `ani`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/ani.webp
- Description: High-fidelity, classic styled anime model.

### Nano Banana Pro (`nano-banana-pro`)

- Model name to send: `nano-banana-pro`
- Creator: Google
- Cost: 28 credits per image (~$0.1316)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 8
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/nanobananapro.webp
- Description: Google's Pro Tier offering on their first-generation Nano Banana model, pushing the bar for high quality image creation, and high precision editing workloads.

### Qwen 2.0 (`qwen-2-0`)

- Model name to send: `qwen-2-0`
- Creator: Alibaba
- Cost: 8 credits per image (~$0.0376)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 3
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/qwen2image.webp
- Description: Qwen 2 by Alibaba packs a punch at entry-level pricing - with detailed text rendering, flexible editing, and great style control.

### Fur (`fur`)

- Model name to send: `fur`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/fur.webp
- Description: Anime-style Furry model.

### Synth (`synth`)

- Model name to send: `synth`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/synth.webp
- Description: Join the Cyberpunk revolution, with a touch of Synthwave to boot!

### Seedream 4.5 (`seedream-4-5`)

- Model name to send: `seedream-4-5`
- Creator: ByteDance
- Cost: 12 credits per image (~$0.0564)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 10
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/seedream45.webp
- Description: Cutting-edge Native 4K model, with full edit capabilities.

### Noob (`noob`)

- Model name to send: `noob`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/noob.webp
- Description: Anime-style model with extreme style range and character recognition - prompt assist highly recommended.

### Aura (`aura`)

- Model name to send: `aura`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/aura.webp
- Description: Create gorgeous artwork in a professional graphic novel illustration style! Prompt assist recommended.

### Pixel (`pixel`)

- Model name to send: `pixel`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/pixel.webp
- Description: Create artwork from the golden age of the pixel art era! [New Pixel Core]

### FLUX.2 Klein 9b (`flux-2-klein-9b`)

- Model name to send: `flux-2-klein-9b`
- Creator: Black Forest Labs
- Cost: 10 credits per image (~$0.0470)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 4
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/klein9b.webp
- Description: FLUX.2's Klein Flagship, HD outputs and full image edit support at an excellent price/performance ratio.

### Nano Banana (`nano-banana`)

- Model name to send: `nano-banana`
- Creator: Google
- Cost: 12 credits per image (~$0.0564)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 6
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9
- Features: text prompts, requires image input, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/alt/image/nanobananaapi_modify.webp
- Description: Google's first-generation image creation and edit model.

### Hyper CGI (`hyper-cgi`)

- Model name to send: `hyper-cgi`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/hypercgi.webp
- Description: Polished CGI Characters, in the style of modern animations.

### FLUX.2 FLEX (`flux-2-flex`)

- Model name to send: `flux-2-flex`
- Creator: Black Forest Labs
- Cost: 28 credits per image (~$0.1316)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 8
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/flux2flex.webp
- Description: FLUX.2's flagship model, built to compete directly with Google's Nano Banana Pro.

### Imagine Art 1.5 Pro (`imagine-art-1-5-pro`)

- Model name to send: `imagine-art-1-5-pro`
- Creator: Imagine Art
- Cost: 14 credits per image (~$0.0658)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:1, 1:3, 3:2, 2:3
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/imagineart.webp
- Description: Imagine Art's high-fidelity native 4K model with lifelike realism, and refined aesthetics

### Volt (`volt`)

- Model name to send: `volt`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/volt.webp
- Description: Anime style characters with a retro palette.

### WAN 2.7 Image (`wan-2-7-image`)

- Model name to send: `wan-2-7-image`
- Creator: Alibaba
- Cost: 6 credits per image (~$0.0282)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 9
- Supported aspects: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/wan27image.webp
- Description: Alibaba's Base WAN 2.7 Image model, bringing WAN's signature best-in-class natural realism at a budget cost!

### GPT Image 1.5 (`gpt-image-1-5`)

- Model name to send: `gpt-image-1-5`
- Creator: OpenAI
- Cost: 32 credits per image (~$0.1504)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/gptimage15.webp
- Description: OpenAI's flagship image model.

### Muse (`muse`)

- Model name to send: `muse`
- Creator: imgnAI
- Cost: 3 credits per image (~$0.0141)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/muse.webp
- Description: Flux-based model fine-tuned on Goths, Emos, and e-girls. Yes, really.

### FLUX.2 PRO (`flux-2-pro`)

- Model name to send: `flux-2-pro`
- Creator: Black Forest Labs
- Cost: 8 credits per image (~$0.0376)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 4
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/flux2pro.webp
- Description: FLUX.2's entry-level model, offering great performance at budget pricing.

### Gothic (`gothic`)

- Model name to send: `gothic`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/gothic.webp
- Description: Dark clothes, dark hair, dark eyeliner. All the best things in an image model.

### Z-Image Base (`z-image-base`)

- Model name to send: `z-image-base`
- Creator: Z.ai
- Cost: 7 credits per image (~$0.0329)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/zimagebase.webp
- Description: Z.ai's foundational image model, built for high quality and generative diversity at budget pricing.

### Z-Image Turbo (`z-image-turbo`)

- Model name to send: `z-image-turbo`
- Creator: Z.ai
- Cost: 4 credits per image (~$0.0188)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/zimageturbo.webp
- Description: Z.ai's Turbo image model, a lightning-fast distillation of Z-Image Base.

### Rend (`rend`)

- Model name to send: `rend`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/rend.webp
- Description: A high-quality blended mix of path-traced rendering, and anime stylization.

### Retro (`retro`)

- Model name to send: `retro`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/retro.webp
- Description: Retro-styled anime, straight from the 90's!

### FLUX.2 Klein 4b (`flux-2-klein-4b`)

- Model name to send: `flux-2-klein-4b`
- Creator: Black Forest Labs
- Cost: 4 credits per image (~$0.0188)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 4
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/klein4b.webp
- Description: FLUX.2's small but powerful Klein 4b model, further extending the cost savings offered with Klein 9b.

### Neo (`neo`)

- Model name to send: `neo`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/neo.webp
- Description: High quality realism & render model optimized for UHD Mode.

### Pony (`pony`)

- Model name to send: `pony`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/pony.webp
- Description: Expressive sketch-like anime model with excellent character recognition.

### Nai (`nai`)

- Model name to send: `nai`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/nai.webp
- Description: Modern, alternative anime style model.

### FLUX 1.1 Ultra (`flux-1-1-ultra`)

- Model name to send: `flux-1-1-ultra`
- Creator: Black Forest Labs
- Cost: 18 credits per image (~$0.0846)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/flux1ultra.webp
- Description: BFL's final FLUX.1 iteration, extremely high quality 4MP outputs.

### Glitch (`glitch`)

- Model name to send: `glitch`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/glitch.webp
- Description: Load up on glitch-burn aesthetics, with this compelling and unique art style!

### Qwen Image (`qwen-image`)

- Model name to send: `qwen-image`
- Creator: Alibaba Cloud
- Cost: 8 credits per image (~$0.0376)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/qwen.webp
- Description: Versatile model with excellent text capabilities.

### Seedream 4 (`seedream-4`)

- Model name to send: `seedream-4`
- Creator: ByteDance
- Cost: 12 credits per image (~$0.0564)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 10
- Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
- Features: text prompts, supports reference images, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/seedream4.webp
- Description: Excellent quality 4K model, with full edit capabilities.

### WAN 2.2 Image (`wan-2-2-image`)

- Model name to send: `wan-2-2-image`
- Creator: Alibaba Cloud
- Cost: 8 credits per image (~$0.0376)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/wan22image.webp
- Description: Stunning still-frame imagery powered by the WAN Video model.

### Flux1.D (`flux1-d`)

- Model name to send: `flux1-d`
- Creator: Black Forest Labs
- Cost: 3 credits per image (~$0.0141)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: text prompts
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/fluxpro.webp
- Description: BFL's general-purpose Flux1.D model.

### Qwen Image Edit (`qwen-image-edit`)

- Model name to send: `qwen-image-edit`
- Creator: Alibaba Cloud
- Cost: 12 credits per image (~$0.0564)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4
- Features: text prompts, requires image input, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/alt/image/qweneditapi_modify.webp
- Description: Super-charged Qwen Image, with full image editing capabilities.

### Supra (`supra`)

- Model name to send: `supra`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/supra2.webp
- Description: Digital render style model, similar to MidJourney v6.

### Evo (`evo`)

- Model name to send: `evo`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/evo.webp
- Description: Slightly abstract realism, flexible model specializing in texture details.

### Toon (`toon`)

- Model name to send: `toon`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/toon.webp
- Description: Western cartoon style model.

### Wassie (`wassie`)

- Model name to send: `wassie`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/wassie.webp
- Description: Create Wassies of all shapes and sizes!

### HyperX (`hyperx`)

- Model name to send: `hyperx`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/hyperx.webp
- Description: Legacy CG-Style renders.

### FurXL Classic (`furxl-classic`)

- Model name to send: `furxl-classic`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/furxl.webp
- Description: Furries in all shapes and sizes!

### Flux Kontext Max (`flux-kontext-max`)

- Model name to send: `flux-kontext-max`
- Creator: Black Forest Labs
- Cost: 20 credits per image (~$0.0940)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
- Features: text prompts, requires image input, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/alt/image/fluxkontextmax_modify.webp
- Description: BFL's legacy high-end image editing model.

### Flux Kontext Pro (`flux-kontext-pro`)

- Model name to send: `flux-kontext-pro`
- Creator: Black Forest Labs
- Cost: 12 credits per image (~$0.0564)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
- Features: text prompts, requires image input, edit/reference workflow
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: send `image_urls` with HTTPS URLs, data URLs, or raw base64 image strings
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/alt/image/fluxkontextpro_modify.webp
- Description: BFL's legacy entry-level image editing model.

### Supra Classic (`supra-classic`)

- Model name to send: `supra-classic`
- Creator: imgnAI
- Cost: 2 credits per image (~$0.0094)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
- Features: standard image generation
- Output format: send `output_format` as `png`, `jpeg`, or `webp`.
- Image inputs: text prompt is the normal workflow; `image_url` or `image_urls` may be accepted where the backend supports it
- Aspect AUTO: send `aspect_ratio: "auto"` to inspect the first image input; with no input it defaults to `1:1` when supported.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/image/supra.webp
- Description: High-range Digital Renders


## Video Models

### Seedance 2.0 (`seedance-2-0`)

- Model name to send: `seedance-2-0`
- Creator: ByteDance
- Duration costs: 5 seconds: 200 credits (~$0.9400); 10 seconds: 375 credits (~$1.76); 15 seconds: 550 credits (~$2.58)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 7
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, last frame, reference images up to 7, audio input up to 3 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 3 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 7 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance2video.webp
- Description: The world's frontier video model, offering unprecedented prompt adherence and audio/video quality.
- Custom rules for this model:
  - Reference images cannot be combined with first-frame or last-frame inputs.
  - Audio input cannot be combined with first-frame or last-frame inputs.
  - Last-frame input requires a first-frame input.
  - Combined selected audio input is limited to 15 seconds.

### Seedance 2.0 (480p) (`seedance-2-0-480p`)

- Model name to send: `seedance-2-0-480p`
- Creator: ByteDance
- Duration costs: 5 seconds: 120 credits (~$0.5640); 10 seconds: 230 credits (~$1.08); 15 seconds: 340 credits (~$1.60)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 7
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, last frame, reference images up to 7, audio input up to 3 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 3 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 7 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance2480pvideo.webp
- Description: All the power of Seedance 2.0's full model - optimized for Mobile resolutions, at half the cost!
- Custom rules for this model:
  - Reference images cannot be combined with first-frame or last-frame inputs.
  - Audio input cannot be combined with first-frame or last-frame inputs.
  - Last-frame input requires a first-frame input.
  - Combined selected audio input is limited to 15 seconds.

### Seedance 2.0 (Fast) (`seedance-2-0-fast`)

- Model name to send: `seedance-2-0-fast`
- Creator: ByteDance
- Duration costs: 5 seconds: 120 credits (~$0.5640); 10 seconds: 230 credits (~$1.08); 15 seconds: 340 credits (~$1.60)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 7
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, last frame, reference images up to 7, audio input up to 3 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 3 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 7 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance2fastvideo.webp
- Description: Seedance 2.0's Fast model, offering a powerful budget entry for full resolution outputs!
- Custom rules for this model:
  - Reference images cannot be combined with first-frame or last-frame inputs.
  - Audio input cannot be combined with first-frame or last-frame inputs.
  - Last-frame input requires a first-frame input.
  - Combined selected audio input is limited to 15 seconds.

### LTX 2.3 (`ltx-2-3`)

- Model name to send: `ltx-2-3`
- Creator: Lightricks
- Duration costs: 5 seconds: 20 credits (~$0.0940); 10 seconds: 40 credits (~$0.1880); 15 seconds: 60 credits (~$0.2820); 20 seconds: 80 credits (~$0.3760)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1
- Features: first frame, last frame, audio input up to 1 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 1 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/ltx23video.webp
- Description: Powerful open source audio-video model by Lightricks - hosted in-house for premium results at dramatically lower prices.
- Custom rules for this model:
  - Audio input can only be used with first-frame conditioning.
  - Video duration follows the selected audio duration.

### Happy Horse 1.0 (1080p) (`happy-horse-1-0-1080p`)

- Model name to send: `happy-horse-1-0-1080p`
- Creator: Alibaba
- Duration costs: 5 seconds: 300 credits (~$1.41); 10 seconds: 600 credits (~$2.82); 15 seconds: 900 credits (~$4.23)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 9
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, reference images up to 9
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: supported, up to 9 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/happyhorse101080pvideo.webp
- Description: Alibaba's newest frontier model; boasts breathtaking quality and prompt adherence, at full 1080p resolutions.
- Custom rules for this model:
  - Reference images cannot be combined with first-frame or last-frame inputs.

### Happy Horse 1.0 (720p) (`happy-horse-1-0-720p`)

- Model name to send: `happy-horse-1-0-720p`
- Creator: Alibaba
- Duration costs: 5 seconds: 150 credits (~$0.7050); 10 seconds: 300 credits (~$1.41); 15 seconds: 450 credits (~$2.12)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 9
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, reference images up to 9
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: supported, up to 9 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/happyhorse10720pvideo.webp
- Description: Alibaba's powerful Happy Horse 1.0 model - retaining breathtaking quality at 720p resolutions, coupled with discounted pricing!
- Custom rules for this model:
  - Reference images cannot be combined with first-frame or last-frame inputs.

### WAN 2.7 (1080p) (`wan-2-7-1080p`)

- Model name to send: `wan-2-7-1080p`
- Creator: Alibaba
- Duration costs: 5 seconds: 130 credits (~$0.6110); 10 seconds: 260 credits (~$1.22)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 5
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, last frame, reference images up to 5, audio input up to 1 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 1 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 5 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/wan271080pvideo.webp
- Description: WAN 2.7 excels in creating videos with breathtaking consistency across reference images, and high-fidelity textures.
- Custom rules for this model:
  - Reference audio is interpreted as voice timbre when reference images are present.
  - Reference images cannot be combined with first-frame or last-frame inputs.

### WAN 2.7 (720p) (`wan-2-7-720p`)

- Model name to send: `wan-2-7-720p`
- Creator: Alibaba
- Duration costs: 5 seconds: 90 credits (~$0.4230); 10 seconds: 180 credits (~$0.8460)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 5
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: first frame, last frame, reference images up to 5, audio input up to 1 file(s)
- Audio output: generates audio by default
- Audio references accepted: yes, up to 1 file(s)
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 5 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/wan27720pvideo.webp
- Description: Alibaba's 720p WAN 2.7 model - retaining excellent quality, at a discounted rate!
- Custom rules for this model:
  - Reference audio is interpreted as voice timbre when reference images are present.
  - Reference images cannot be combined with first-frame or last-frame inputs.

### Kling O3 4K (`kling-o3-4k`)

- Model name to send: `kling-o3-4k`
- Creator: Kling AI
- Duration costs: 5 seconds: 450 credits (~$2.12); 10 seconds: 900 credits (~$4.23); 15 seconds: 1350 credits (~$6.35)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 6
- Supported aspects: 16:9, 9:16, 1:1
- Features: first frame, last frame, reference images up to 6
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 6 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling304kvideo.webp
- Description: Kling's flagship O3 model, in astonishing 4K Quality!
- Custom rules for this model: none

### Kling 3.0 (`kling-3-0-kling30pro`)

- Model name to send: `kling-3-0-kling30pro`
- Creator: Kling AI
- Duration costs: 5 seconds: 350 credits (~$1.65); 10 seconds: 650 credits (~$3.06); 15 seconds: 925 credits (~$4.35)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 6
- Supported aspects: 16:9, 9:16, 1:1
- Features: first frame, last frame, reference images up to 6
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 6 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling30provideo.webp
- Description: Kling's flagship 3.0 model, pairing excellent prompt adherence with industry quality audio/video output.
- Custom rules for this model: none

### Kling 3.0 (`kling-3-0-kling30`)

- Model name to send: `kling-3-0-kling30`
- Creator: Kling AI
- Duration costs: 5 seconds: 280 credits (~$1.32); 10 seconds: 550 credits (~$2.58); 15 seconds: 800 credits (~$3.76)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 6
- Supported aspects: 16:9, 9:16, 1:1
- Features: first frame, last frame, reference images up to 6
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: supported
- Reference image input: supported, up to 6 image(s)
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling30video.webp
- Description: Kling's cutting-edge 3.0 model, with great prompt adherence, and stellar quality audio/video output.
- Custom rules for this model: none

### Veo3.1 (`veo3-1`)

- Model name to send: `veo3-1`
- Creator: Google
- Duration costs: 4 seconds: 380 credits (~$1.79); 8 seconds: 750 credits (~$3.53)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16
- Features: first frame
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/veo3video.webp
- Description: Google's updated Veo3.1 model, showcasing 1080p cinematic quality video, with full audio support.
- Custom rules for this model: none

### Veo3.1 Fast (`veo3-1-fast`)

- Model name to send: `veo3-1-fast`
- Creator: Google
- Duration costs: 4 seconds: 160 credits (~$0.7520); 8 seconds: 300 credits (~$1.41)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16
- Features: first frame
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/veo3videofast.webp
- Description: Veo 3.1's little brother - bringing high speeds at lower costs, while still offering superb quality audio/video generation.
- Custom rules for this model: none

### Veo3.1 Lite (`veo3-1-lite`)

- Model name to send: `veo3-1-lite`
- Creator: Google
- Duration costs: 8 seconds: 140 credits (~$0.6580)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16
- Features: first frame
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/veo3videolite.webp
- Description: Google's latest offering in their Veo3.1 line, packing excellent quality at an incredibly low cost!
- Custom rules for this model: none

### Seedance Pro (`seedance-pro`)

- Model name to send: `seedance-pro`
- Creator: ByteDance
- Duration costs: 5 seconds: 250 credits (~$1.18); 10 seconds: 450 credits (~$2.12)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance1provideo.webp
- Description: Excellent quality HD outputs across a range of styles, with excellent prompt adherence.
- Custom rules for this model: none

### WAN 2.5 (`wan-2-5`)

- Model name to send: `wan-2-5`
- Creator: Alibaba Cloud
- Duration costs: 5 seconds: 220 credits (~$1.03); 10 seconds: 400 credits (~$1.88)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
- Features: first frame
- Audio output: generates audio by default
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/wan25video.webp
- Description: Excellent quality HD outputs with full audio generation, at a stunningly low cost.
- Custom rules for this model: none

### Hailuo 2 (MiniMax) (`hailuo-2-minimax`)

- Model name to send: `hailuo-2-minimax`
- Creator: Hailuo AI
- Duration costs: 6 seconds: 200 credits (~$0.9400)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/minimax2video.webp
- Description: Great quality at competitive pricing, excels at text rendering.
- Custom rules for this model: none

### Kling 2.1 (`kling-2-1-kling21`)

- Model name to send: `kling-2-1-kling21`
- Creator: Kling AI
- Duration costs: 5 seconds: 160 credits (~$0.7520); 10 seconds: 300 credits (~$1.41)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling21video.webp
- Description: Quality close to Kling's master 2.0 model, at budget pricing.
- Custom rules for this model: none

### Kling 2.1 (`kling-2-1-kling21loop`)

- Model name to send: `kling-2-1-kling21loop`
- Creator: Kling AI
- Duration costs: 5 seconds: 160 credits (~$0.7520); 10 seconds: 300 credits (~$1.41)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling21loopedvideo.webp
- Description: Infinitely looped videos with Kling 2.1!
- Custom rules for this model: none

### Seedance Lite (`seedance-lite-seedancelite`)

- Model name to send: `seedance-lite-seedancelite`
- Creator: ByteDance
- Duration costs: 5 seconds: 120 credits (~$0.5640); 10 seconds: 200 credits (~$0.9400)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance1litevideo.webp
- Description: Exceptional cost-to-performance video model.
- Custom rules for this model: none

### Seedance Lite (`seedance-lite-seedanceliteloop`)

- Model name to send: `seedance-lite-seedanceliteloop`
- Creator: ByteDance
- Duration costs: 5 seconds: 120 credits (~$0.5640); 10 seconds: 200 credits (~$0.9400)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/seedance1liteloopedvideo.webp
- Description: Infinitely looped videos with Seedance Lite!
- Custom rules for this model: none

### Kling 2.0 (`kling-2-0`)

- Model name to send: `kling-2-0`
- Creator: Kling AI
- Duration costs: 5 seconds: 350 credits (~$1.65); 10 seconds: 650 credits (~$3.06)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling2video.webp
- Description: Kling's raw/master 2.0 video model. Excellent quality, but very highly priced for video-only.
- Custom rules for this model: none

### Kling 1.6 (`kling-1-6`)

- Model name to send: `kling-1-6`
- Creator: Kling AI
- Duration costs: 5 seconds: 130 credits (~$0.6110); 10 seconds: 250 credits (~$1.18)
- x402: supported with Base USDC and Solana USDC. Call without API-key headers to receive exact payment requirements.
- Reference images supported: 0
- Supported aspects: 16:9, 9:16, 1:1
- Features: requires image input, first frame
- Audio output: silent/no generated audio
- Audio references accepted: no
- First frame input: supported
- Mid frame input: not supported
- Last frame input: not supported
- Reference image input: not supported
- Image input value format: HTTPS URL, `data:image/...;base64,...` data URL, or raw base64 image string for supported image/frame/reference slots.
- Thumbnail: https://wasmall.imgnai.com/static/thumbnails/video/kling16video.webp
- Description: [Legacy] Kling's early-era 1.6 video generation model.
- Custom rules for this model: none


## Copy for LLMs Catalog

The section below mirrors the richer per-model integration guide exposed by the documentation UI's Copy for LLMs action. It is included here so `/llms.txt` can be used as the single source of truth for LLM and coding-agent integrations.

# imgnAI model catalog

This document is self-contained and intended for another LLM or coding agent integrating with imgnAI.
Base URL: http://devkat.imgnai.com
API key management: https://app.imgnai.com/api
Credits and subscriptions: https://app.imgnai.com
Reference price: $0.0047 per credit, based on Platinum Annual pricing.

For text models, call POST /v1/chat/completions with Authorization: Bearer <api_key>:<api_secret>. For image and video, call POST /v1/generation-requests?wait=true with X-API-Key and X-API-Secret headers. Use wait=false and poll GET /v1/generation-requests/{request_id} for asynchronous flows.

# imgnAI model integration guide: Grok 4.3

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Grok 4.3
Model name to send: grok-4-3
Request type: text
Publisher / creator: xAI
Description: Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Cost: 292.6 credits / 1M input tokens (US$1.38); 585.2 credits / 1M output tokens (US$2.75)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `grok-4-3`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text, image
- Context length: 1000000 tokens
- Release date: 2026-04-30
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "grok-4-3",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "grok-4-3",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.6 35B A3B

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.6 35B A3B
Model name to send: qwen3-6-35b-a3b
Request type: text
Publisher / creator: Qwen
Description: Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Cost: 35.2 credits / 1M input tokens (US$0.1650); 234.1 credits / 1M output tokens (US$1.10)
Supported aspects: not applicable
Supported input types: text, image, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-6-35b-a3b`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: Anonymized
- Input types: text, image, video
- Context length: 262144 tokens
- Release date: 2026-04-27
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-6-35b-a3b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-6-35b-a3b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.6 Flash

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.6 Flash
Model name to send: qwen3-6-flash
Request type: text
Publisher / creator: Qwen
Description: Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
Cost: 58.6 credits / 1M input tokens (US$0.2750); 351.1 credits / 1M output tokens (US$1.65)
Supported aspects: not applicable
Supported input types: text, image, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-6-flash`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, presence_penalty, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
- Privacy: Anonymized
- Input types: text, image, video
- Context length: 1000000 tokens
- Release date: 2026-04-27
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-6-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-6-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.6 Max Preview

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.6 Max Preview
Model name to send: qwen3-6-max-preview
Request type: text
Publisher / creator: Qwen
Description: Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...
Cost: 243.5 credits / 1M input tokens (US$1.14); 1460.5 credits / 1M output tokens (US$6.86)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-6-max-preview`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 262144 tokens
- Release date: 2026-04-27

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-6-max-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-6-max-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: DeepSeek V4 Flash

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: DeepSeek V4 Flash
Model name to send: deepseek-v4-flash
Request type: text
Publisher / creator: DeepSeek
Description: DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Cost: 32.8 credits / 1M input tokens (US$0.1540); 65.6 credits / 1M output tokens (US$0.3080)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `deepseek-v4-flash`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 1048576 tokens
- Release date: 2026-04-24

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: DeepSeek V4 Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: DeepSeek V4 Pro
Model name to send: deepseek-v4-pro
Request type: text
Publisher / creator: DeepSeek
Description: DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Cost: 101.9 credits / 1M input tokens (US$0.4785); 203.7 credits / 1M output tokens (US$0.9570)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `deepseek-v4-pro`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 1048576 tokens
- Release date: 2026-04-24

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GPT-5.5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GPT-5.5
Model name to send: gpt-5-5
Request type: text
Publisher / creator: OpenAI
Description: GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
Cost: 1170.3 credits / 1M input tokens (US$5.50); 7021.3 credits / 1M output tokens (US$33.00)
Supported aspects: not applicable
Supported input types: file, image, text
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gpt-5-5`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, seed, structured_outputs, tool_choice, tools
- Privacy: Anonymized
- Input types: file, image, text
- Context length: 1050000 tokens
- Release date: 2026-04-24
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gpt-5-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gpt-5-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Kimi K2.6 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kimi K2.6 Private
Model name to send: kimi-k2-6-private
Request type: text
Publisher / creator: MoonshotAI
Description: Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and demonstrates strong performance in agentic workflows.
Cost: 255.2 credits / 1M input tokens (US$1.20); 1076.6 credits / 1M output tokens (US$5.06)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `kimi-k2-6-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text, image
- Context length: 262144 tokens
- Release date: 2026-04-21
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "kimi-k2-6-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "kimi-k2-6-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3 Coder Next Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3 Coder Next Private
Model name to send: qwen3-coder-next-private
Request type: text
Publisher / creator: Qwen
Description: Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering competitive performance with efficient inference.
Cost: 42.2 credits / 1M input tokens (US$0.1980); 280.9 credits / 1M output tokens (US$1.32)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-coder-next-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 262144 tokens
- Release date: 2026-04-21
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-coder-next-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-coder-next-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GLM 5.1 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GLM 5.1 Private
Model name to send: glm-5-1-private
Request type: text
Publisher / creator: Z.ai
Description: GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
Cost: 283.2 credits / 1M input tokens (US$1.33); 983.0 credits / 1M output tokens (US$4.62)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `glm-5-1-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 202752 tokens
- Release date: 2026-04-20
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "glm-5-1-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "glm-5-1-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Kimi K2.6

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kimi K2.6
Model name to send: kimi-k2-6
Request type: text
Publisher / creator: MoonshotAI
Description: Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Cost: 175.6 credits / 1M input tokens (US$0.8250); 819.2 credits / 1M output tokens (US$3.85)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `kimi-k2-6`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text, image
- Context length: 262144 tokens
- Release date: 2026-04-20
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "kimi-k2-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "kimi-k2-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: MiMo-V2-Flash Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: MiMo-V2-Flash Private
Model name to send: mimo-v2-flash-private
Request type: text
Publisher / creator: Xiaomi
Description: MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a...
Cost: 23.5 credits / 1M input tokens (US$0.1100); 70.3 credits / 1M output tokens (US$0.3300)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `mimo-v2-flash-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, temperature, tool_choice, tools, top_k, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 262144 tokens
- Release date: 2026-04-20
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "mimo-v2-flash-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "mimo-v2-flash-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Claude Opus 4.7

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Claude Opus 4.7
Model name to send: claude-opus-4-7
Request type: text
Publisher / creator: Anthropic
Description: Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
Cost: 1170.3 credits / 1M input tokens (US$5.50); 5851.1 credits / 1M output tokens (US$27.50)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `claude-opus-4-7`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, reasoning, response_format, stop, structured_outputs, tool_choice, tools, verbosity
- Privacy: Anonymized
- Input types: text, image
- Context length: 1000000 tokens
- Release date: 2026-04-16
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "claude-opus-4-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "claude-opus-4-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GLM 5.1

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GLM 5.1
Model name to send: glm-5-1
Request type: text
Publisher / creator: Z.ai
Description: GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
Cost: 245.8 credits / 1M input tokens (US$1.16); 819.2 credits / 1M output tokens (US$3.85)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `glm-5-1`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 202752 tokens
- Release date: 2026-04-07

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "glm-5-1",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "glm-5-1",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemma 4 26B A4B

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemma 4 26B A4B
Model name to send: gemma-4-26b-a4b
Request type: text
Publisher / creator: Google
Description: Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Cost: 14.1 credits / 1M input tokens (US$0.0660); 77.3 credits / 1M output tokens (US$0.3630)
Supported aspects: not applicable
Supported input types: image, text, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gemma-4-26b-a4b`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: image, text, video
- Context length: 262144 tokens
- Release date: 2026-04-03
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemma-4-26b-a4b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemma-4-26b-a4b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemma 4 31B

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemma 4 31B
Model name to send: gemma-4-31b
Request type: text
Publisher / creator: Google
Description: Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Cost: 30.5 credits / 1M input tokens (US$0.1430); 89.0 credits / 1M output tokens (US$0.4180)
Supported aspects: not applicable
Supported input types: image, text, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gemma-4-31b`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: image, text, video
- Context length: 262144 tokens
- Release date: 2026-04-02
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemma-4-31b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemma-4-31b",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.6 Plus

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.6 Plus
Model name to send: qwen3-6-plus
Request type: text
Publisher / creator: Qwen
Description: Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
Cost: 76.1 credits / 1M input tokens (US$0.3575); 456.4 credits / 1M output tokens (US$2.15)
Supported aspects: not applicable
Supported input types: text, image, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-6-plus`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, presence_penalty, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p
- Privacy: Anonymized
- Input types: text, image, video
- Context length: 1000000 tokens
- Release date: 2026-04-02
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-6-plus",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-6-plus",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Grok 4.20

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Grok 4.20
Model name to send: grok-4-20
Request type: text
Publisher / creator: xAI
Description: Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Cost: 292.6 credits / 1M input tokens (US$1.38); 585.2 credits / 1M output tokens (US$2.75)
Supported aspects: not applicable
Supported input types: text, image, file
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `grok-4-20`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, logprobs, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text, image, file
- Context length: 2000000 tokens
- Release date: 2026-03-31
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "grok-4-20",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "grok-4-20",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Grok 4.20 Multi-Agent

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Grok 4.20 Multi-Agent
Model name to send: grok-4-20-multi-agent
Request type: text
Publisher / creator: xAI
Description: Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
Cost: 468.1 credits / 1M input tokens (US$2.20); 1404.3 credits / 1M output tokens (US$6.60)
Supported aspects: not applicable
Supported input types: text, image, file
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Structured output, Long context

## Request fields and behavior

- model: Required. Send `grok-4-20-multi-agent`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, logprobs, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text, image, file
- Context length: 2000000 tokens
- Release date: 2026-03-31
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "grok-4-20-multi-agent",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": null
}
```

## Minimal practical sample

```json
{
  "model": "grok-4-20-multi-agent",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: MiniMax M2.7

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: MiniMax M2.7
Model name to send: minimax-m2-7
Request type: text
Publisher / creator: MiniMax
Description: MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
Cost: 70.0 credits / 1M input tokens (US$0.3289); 280.9 credits / 1M output tokens (US$1.32)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output

## Request fields and behavior

- model: Required. Send `minimax-m2-7`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 196608 tokens
- Release date: 2026-03-18

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "minimax-m2-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "minimax-m2-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GPT-5.4 Mini

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GPT-5.4 Mini
Model name to send: gpt-5-4-mini
Request type: text
Publisher / creator: OpenAI
Description: GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
Cost: 175.6 credits / 1M input tokens (US$0.8250); 1053.2 credits / 1M output tokens (US$4.95)
Supported aspects: not applicable
Supported input types: file, image, text
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gpt-5-4-mini`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, seed, structured_outputs, tool_choice, tools
- Privacy: Anonymized
- Input types: file, image, text
- Context length: 400000 tokens
- Release date: 2026-03-17
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gpt-5-4-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gpt-5-4-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GLM 5 Turbo

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GLM 5 Turbo
Model name to send: glm-5-turbo
Request type: text
Publisher / creator: Z.ai
Description: GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
Cost: 280.9 credits / 1M input tokens (US$1.32); 936.2 credits / 1M output tokens (US$4.40)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `glm-5-turbo`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, temperature, tool_choice, tools, top_k, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 202752 tokens
- Release date: 2026-03-15

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "glm-5-turbo",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "glm-5-turbo",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.5-27B Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.5-27B Private
Model name to send: qwen3-5-27b-private
Request type: text
Publisher / creator: Qwen
Description: The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.
Cost: 70.3 credits / 1M input tokens (US$0.3300); 561.8 credits / 1M output tokens (US$2.64)
Supported aspects: not applicable
Supported input types: text, image, video
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-5-27b-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text, image, video
- Context length: 262144 tokens
- Release date: 2026-03-13
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-5-27b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-5-27b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GPT-5.4

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GPT-5.4
Model name to send: gpt-5-4
Request type: text
Publisher / creator: OpenAI
Description: GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Cost: 585.2 credits / 1M input tokens (US$2.75); 3510.7 credits / 1M output tokens (US$16.50)
Supported aspects: not applicable
Supported input types: text, image, file
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gpt-5-4`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, seed, structured_outputs, tool_choice, tools
- Privacy: Anonymized
- Input types: text, image, file
- Context length: 1050000 tokens
- Release date: 2026-03-05
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gpt-5-4",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gpt-5-4",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemini 3.1 Flash Lite Preview

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemini 3.1 Flash Lite Preview
Model name to send: gemini-3-1-flash-lite-preview
Request type: text
Publisher / creator: Google
Description: Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
Cost: 58.6 credits / 1M input tokens (US$0.2750); 351.1 credits / 1M output tokens (US$1.65)
Supported aspects: not applicable
Supported input types: text, image, video, file, audio
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gemini-3-1-flash-lite-preview`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
- Privacy: Anonymized
- Input types: text, image, video, file, audio
- Context length: 1048576 tokens
- Release date: 2026-03-03
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.
- Audio: Supported by the upstream-compatible content shape for this model when the provider accepts audio inputs.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemini-3-1-flash-lite-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemini-3-1-flash-lite-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3.5 397B A17B Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3.5 397B A17B Private
Model name to send: qwen3-5-397b-a17b-private
Request type: text
Publisher / creator: Qwen
Description: The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.
Cost: 128.8 credits / 1M input tokens (US$0.6050); 819.2 credits / 1M output tokens (US$3.85)
Supported aspects: not applicable
Supported input types: text, image, video
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `qwen3-5-397b-a17b-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text, image, video
- Context length: 262144 tokens
- Release date: 2026-02-28
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-5-397b-a17b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-5-397b-a17b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: MiniMax M2.5 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: MiniMax M2.5 Private
Model name to send: minimax-m2-5-private
Request type: text
Publisher / creator: MiniMax
Description: MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
Cost: 46.9 credits / 1M input tokens (US$0.2200); 323.0 credits / 1M output tokens (US$1.52)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output

## Request fields and behavior

- model: Required. Send `minimax-m2-5-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 196608 tokens
- Release date: 2026-02-21
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "minimax-m2-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "minimax-m2-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemini 3.1 Pro Preview

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemini 3.1 Pro Preview
Model name to send: gemini-3-1-pro-preview
Request type: text
Publisher / creator: Google
Description: Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
Cost: 468.1 credits / 1M input tokens (US$2.20); 2808.6 credits / 1M output tokens (US$13.20)
Supported aspects: not applicable
Supported input types: audio, file, image, text, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gemini-3-1-pro-preview`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
- Privacy: Anonymized
- Input types: audio, file, image, text, video
- Context length: 1048576 tokens
- Release date: 2026-02-19
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.
- Audio: Supported by the upstream-compatible content shape for this model when the provider accepts audio inputs.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemini-3-1-pro-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemini-3-1-pro-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Claude Sonnet 4.6

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Claude Sonnet 4.6
Model name to send: claude-sonnet-4-6
Request type: text
Publisher / creator: Anthropic
Description: Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
Cost: 702.2 credits / 1M input tokens (US$3.30); 3510.7 credits / 1M output tokens (US$16.50)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `claude-sonnet-4-6`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p, verbosity
- Privacy: Anonymized
- Input types: text, image
- Context length: 1000000 tokens
- Release date: 2026-02-17
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "claude-sonnet-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "claude-sonnet-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GLM 5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GLM 5
Model name to send: glm-5
Request type: text
Publisher / creator: Z.ai
Description: GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
Cost: 140.5 credits / 1M input tokens (US$0.6600); 449.4 credits / 1M output tokens (US$2.11)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: Anonymized, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `glm-5`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: Anonymized
- Input types: text
- Context length: 202752 tokens
- Release date: 2026-02-11

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "glm-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "glm-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GLM 5 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GLM 5 Private
Model name to send: glm-5-private
Request type: text
Publisher / creator: Z.ai
Description: GLM-5 is an open-source foundation model built for complex systems engineering and long-horizon agent workflows. It delivers production-grade productivity for large-scale programming tasks, with performance aligned to top closed-source models, and is designed for expert developers building at the system level.
Cost: 280.9 credits / 1M input tokens (US$1.32); 819.2 credits / 1M output tokens (US$3.85)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `glm-5-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 202752 tokens
- Release date: 2026-02-10
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "glm-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "glm-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Claude Opus 4.6

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Claude Opus 4.6
Model name to send: claude-opus-4-6
Request type: text
Publisher / creator: Anthropic
Description: Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Cost: 1170.3 credits / 1M input tokens (US$5.50); 5851.1 credits / 1M output tokens (US$27.50)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `claude-opus-4-6`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_completion_tokens, max_tokens, reasoning, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p, verbosity
- Privacy: Anonymized
- Input types: text, image
- Context length: 1000000 tokens
- Release date: 2026-02-04
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "claude-opus-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "claude-opus-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Kimi K2.5 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kimi K2.5 Private
Model name to send: kimi-k2-5-private
Request type: text
Publisher / creator: MoonshotAI
Description: Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.
Cost: 140.5 credits / 1M input tokens (US$0.6600); 702.2 credits / 1M output tokens (US$3.30)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `kimi-k2-5-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Privacy: E2EE Private
- Input types: text, image
- Context length: 262144 tokens
- Release date: 2026-01-29
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "kimi-k2-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "kimi-k2-5-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemini 3 Flash Preview

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemini 3 Flash Preview
Model name to send: gemini-3-flash-preview
Request type: text
Publisher / creator: Google
Description: Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Cost: 117.1 credits / 1M input tokens (US$0.5500); 702.2 credits / 1M output tokens (US$3.30)
Supported aspects: not applicable
Supported input types: text, image, file, audio, video
Image input support: supported
User-facing capabilities: Anonymized, Vision, File input, Audio input, Video input, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `gemini-3-flash-preview`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
- Privacy: Anonymized
- Input types: text, image, file, audio, video
- Context length: 1048576 tokens
- Release date: 2025-12-17
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Files: Supported by the upstream-compatible content shape for this model when the provider accepts file inputs.
- Audio: Supported by the upstream-compatible content shape for this model when the provider accepts audio inputs.
- Video: Supported by the upstream-compatible content shape for this model when the provider accepts video inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemini-3-flash-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemini-3-flash-preview",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: DeepSeek V3.2 Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: DeepSeek V3.2 Private
Model name to send: deepseek-v3-2-private
Request type: text
Publisher / creator: DeepSeek
Description: DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Cost: 74.9 credits / 1M input tokens (US$0.3520); 112.4 credits / 1M output tokens (US$0.5280)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Tool calling, Structured output

## Request fields and behavior

- model: Required. Send `deepseek-v3-2-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: E2EE Private
- Input types: text
- Context length: 163840 tokens
- Release date: 2025-12-03
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "deepseek-v3-2-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "deepseek-v3-2-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3 Coder 480B A35B Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3 Coder 480B A35B Private
Model name to send: qwen3-coder-480b-a35b-private
Request type: text
Publisher / creator: Qwen
Description: Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).
Cost: 468.1 credits / 1M input tokens (US$2.20); 468.1 credits / 1M output tokens (US$2.20)
Supported aspects: not applicable
Supported input types: text
Image input support: not supported
User-facing capabilities: E2EE Private, Long context

## Request fields and behavior

- model: Required. Send `qwen3-coder-480b-a35b-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: provider defaults only
- Privacy: E2EE Private
- Input types: text
- Context length: 262000 tokens
- Release date: 2025-11-28
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-coder-480b-a35b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": null,
  "tools": null
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-coder-480b-a35b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Qwen3 VL 30B A3B Instruct Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen3 VL 30B A3B Instruct Private
Model name to send: qwen3-vl-30b-a3b-instruct-private
Request type: text
Publisher / creator: Qwen
Description: Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.
Cost: 46.9 credits / 1M input tokens (US$0.2200); 163.9 credits / 1M output tokens (US$0.7700)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Tool calling, Structured output

## Request fields and behavior

- model: Required. Send `qwen3-vl-30b-a3b-instruct-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: E2EE Private
- Input types: text, image
- Context length: 128000 tokens
- Release date: 2025-11-28
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "qwen3-vl-30b-a3b-instruct-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "qwen3-vl-30b-a3b-instruct-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Claude Haiku 4.5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Claude Haiku 4.5
Model name to send: claude-haiku-4-5
Request type: text
Publisher / creator: Anthropic
Description: Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Cost: 234.1 credits / 1M input tokens (US$1.10); 1170.3 credits / 1M output tokens (US$5.50)
Supported aspects: not applicable
Supported input types: image, text
Image input support: supported
User-facing capabilities: Anonymized, Vision, Tool calling, Structured output, Long context

## Request fields and behavior

- model: Required. Send `claude-haiku-4-5`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: include_reasoning, max_tokens, reasoning, response_format, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: Anonymized
- Input types: image, text
- Context length: 200000 tokens
- Release date: 2025-10-15
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "claude-haiku-4-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "claude-haiku-4-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: Gemma 3 27B Private

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gemma 3 27B Private
Model name to send: gemma-3-27b-private
Request type: text
Publisher / creator: Google
Description: Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)
Cost: 25.8 credits / 1M input tokens (US$0.1210); 93.7 credits / 1M output tokens (US$0.4400)
Supported aspects: not applicable
Supported input types: text, image
Image input support: supported
User-facing capabilities: E2EE Private, Vision, Tool calling, Structured output

## Request fields and behavior

- model: Required. Send `gemma-3-27b-private`.
- messages: Required. OpenAI-style chat messages with role/content. Content may be a string or multimodal content parts.
- prompt: Optional compatibility fallback. If messages is omitted and prompt is a string, the API sends it as a single user message.
- stream: Optional boolean. When true, the endpoint returns Server-Sent Events and finalizes billing from the stream usage chunk before [DONE].
- max_tokens / max_completion_tokens: Optional but recommended. The API may apply a conservative default cap when omitted so the reserve can protect against unpaid compute.
- temperature / top_p: Optional if the selected model lists those supported parameters.
- tools / tool_choice: Optional on models that support tool calling. Use OpenAI-compatible function tool schemas.
- response_format: Optional on models that support structured output. Use OpenAI-compatible response_format values.
- Supported parameters: frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
- Privacy: E2EE Private
- Input types: text, image
- Context length: 53920 tokens
- Release date: 2025-10-03
- Images: Supported through OpenAI image_url content parts. HTTPS URLs, data URLs, and raw base64 strings are accepted; base64 inputs are converted to JPEG with max side 4096px.
- Private hardware: Intel TDX, NVIDIA Confidential Computing
- Privacy proof: Use /v1/text/attestation with this public model name to request hardware privacy proof metadata.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "model": "gemma-3-27b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three-sentence launch plan for a small product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4,
  "stream": false,
  "response_format": {
    "type": "json_object"
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "record_plan",
        "description": "Record the generated launch plan.",
        "parameters": {
          "type": "object",
          "properties": {
            "summary": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "model": "gemma-3-27b-private",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Write a three bullet launch checklist for a product API."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.4
}
```

# imgnAI model integration guide: GPT Image 2

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GPT Image 2
Model name to send: gpt-image-2
Request type: image
Publisher / creator: OpenAI
Description: OpenAI's latest and greatest Image Generation & Editing model, delivering a massive leap forward in prompt adherence, stylistic control, and text rendering!
Cost: 14 credits per image (~$0.0658)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 16
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 16 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "gpt-image-2-full",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "gpt-image-2-example",
      "type": "image",
      "model": "gpt-image-2",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Nano Banana 2

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Nano Banana 2
Model name to send: nano-banana-2
Request type: image
Publisher / creator: Google
Description: Google's frontier image creation and edit model, showcasing unprecedented quality and prompt adherence, along with in-built full web search capabilities!
Cost: 32 credits per image (~$0.1504)
Supported aspects: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Supported input types: not listed
Reference Images Supported: 14
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 14 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "nano-banana-2-full",
      "type": "image",
      "model": "nano-banana-2",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "21:9",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "nano-banana-2-example",
      "type": "image",
      "model": "nano-banana-2",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "21:9",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Gen

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gen
Model name to send: gen
Request type: image
Publisher / creator: imgnAI
Description: Our flexible, general-purpose model for any style or subject.
Cost: 3 credits per image (~$0.0141)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "gen-full",
      "type": "image",
      "model": "gen",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "gen-example",
      "type": "image",
      "model": "gen",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Seedream 5.0 Lite

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedream 5.0 Lite
Model name to send: seedream-5-0-lite
Request type: image
Publisher / creator: ByteDance
Description: ByteDance's lightweight, next-gen Image model - with full edit and reference capabilities!
Cost: 7 credits per image (~$0.0329)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 10
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 10 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "seedream-5-0-lite-full",
      "type": "image",
      "model": "seedream-5-0-lite",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "seedream-5-0-lite-example",
      "type": "image",
      "model": "seedream-5-0-lite",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.7 Image Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.7 Image Pro
Model name to send: wan-2-7-image-pro
Request type: image
Publisher / creator: Alibaba
Description: Alibaba's WAN 2.7 Image Pro model, merging true-to-life realism with full reference & edit capabilities.
Cost: 14 credits per image (~$0.0658)
Supported aspects: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 9
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 9 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "wan-2-7-image-pro-full",
      "type": "image",
      "model": "wan-2-7-image-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "wan-2-7-image-pro-example",
      "type": "image",
      "model": "wan-2-7-image-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Ani

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Ani
Model name to send: ani
Request type: image
Publisher / creator: imgnAI
Description: High-fidelity, classic styled anime model.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "ani-full",
      "type": "image",
      "model": "ani",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "ani-example",
      "type": "image",
      "model": "ani",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Nano Banana Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Nano Banana Pro
Model name to send: nano-banana-pro
Request type: image
Publisher / creator: Google
Description: Google's Pro Tier offering on their first-generation Nano Banana model, pushing the bar for high quality image creation, and high precision editing workloads.
Cost: 28 credits per image (~$0.1316)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 8
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 8 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "nano-banana-pro-full",
      "type": "image",
      "model": "nano-banana-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "nano-banana-pro-example",
      "type": "image",
      "model": "nano-banana-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Qwen 2.0

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen 2.0
Model name to send: qwen-2-0
Request type: image
Publisher / creator: Alibaba
Description: Qwen 2 by Alibaba packs a punch at entry-level pricing - with detailed text rendering, flexible editing, and great style control.
Cost: 8 credits per image (~$0.0376)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 3
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 3 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "qwen-2-0-full",
      "type": "image",
      "model": "qwen-2-0",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "qwen-2-0-example",
      "type": "image",
      "model": "qwen-2-0",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Fur

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Fur
Model name to send: fur
Request type: image
Publisher / creator: imgnAI
Description: Anime-style Furry model.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "fur-full",
      "type": "image",
      "model": "fur",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "fur-example",
      "type": "image",
      "model": "fur",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Synth

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Synth
Model name to send: synth
Request type: image
Publisher / creator: imgnAI
Description: Join the Cyberpunk revolution, with a touch of Synthwave to boot!
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "synth-full",
      "type": "image",
      "model": "synth",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "synth-example",
      "type": "image",
      "model": "synth",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Seedream 4.5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedream 4.5
Model name to send: seedream-4-5
Request type: image
Publisher / creator: ByteDance
Description: Cutting-edge Native 4K model, with full edit capabilities.
Cost: 12 credits per image (~$0.0564)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
Supported input types: not listed
Reference Images Supported: 10
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 10 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "seedream-4-5-full",
      "type": "image",
      "model": "seedream-4-5",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "seedream-4-5-example",
      "type": "image",
      "model": "seedream-4-5",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Noob

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Noob
Model name to send: noob
Request type: image
Publisher / creator: imgnAI
Description: Anime-style model with extreme style range and character recognition - prompt assist highly recommended.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "noob-full",
      "type": "image",
      "model": "noob",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "noob-example",
      "type": "image",
      "model": "noob",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Aura

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Aura
Model name to send: aura
Request type: image
Publisher / creator: imgnAI
Description: Create gorgeous artwork in a professional graphic novel illustration style! Prompt assist recommended.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "aura-full",
      "type": "image",
      "model": "aura",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "aura-example",
      "type": "image",
      "model": "aura",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Pixel

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Pixel
Model name to send: pixel
Request type: image
Publisher / creator: imgnAI
Description: Create artwork from the golden age of the pixel art era! [New Pixel Core]
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "pixel-full",
      "type": "image",
      "model": "pixel",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "pixel-example",
      "type": "image",
      "model": "pixel",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FLUX.2 Klein 9b

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FLUX.2 Klein 9b
Model name to send: flux-2-klein-9b
Request type: image
Publisher / creator: Black Forest Labs
Description: FLUX.2's Klein Flagship, HD outputs and full image edit support at an excellent price/performance ratio.
Cost: 10 credits per image (~$0.0470)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
Supported input types: not listed
Reference Images Supported: 4
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 4 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-2-klein-9b-full",
      "type": "image",
      "model": "flux-2-klein-9b",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-2-klein-9b-example",
      "type": "image",
      "model": "flux-2-klein-9b",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Nano Banana

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Nano Banana
Model name to send: nano-banana
Request type: image
Publisher / creator: Google
Description: Google's first-generation image creation and edit model.
Cost: 12 credits per image (~$0.0564)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9
Supported input types: not listed
Reference Images Supported: 6
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language, Requires image

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Required. Provide an image URL, data URL, or raw base64 image string in image_urls. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 6 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "nano-banana-full",
      "type": "image",
      "model": "nano-banana",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "nano-banana-example",
      "type": "image",
      "model": "nano-banana",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Hyper CGI

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Hyper CGI
Model name to send: hyper-cgi
Request type: image
Publisher / creator: imgnAI
Description: Polished CGI Characters, in the style of modern animations.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "hyper-cgi-full",
      "type": "image",
      "model": "hyper-cgi",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "hyper-cgi-example",
      "type": "image",
      "model": "hyper-cgi",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FLUX.2 FLEX

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FLUX.2 FLEX
Model name to send: flux-2-flex
Request type: image
Publisher / creator: Black Forest Labs
Description: FLUX.2's flagship model, built to compete directly with Google's Nano Banana Pro.
Cost: 28 credits per image (~$0.1316)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9
Supported input types: not listed
Reference Images Supported: 8
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 8 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-2-flex-full",
      "type": "image",
      "model": "flux-2-flex",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-2-flex-example",
      "type": "image",
      "model": "flux-2-flex",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Imagine Art 1.5 Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Imagine Art 1.5 Pro
Model name to send: imagine-art-1-5-pro
Request type: image
Publisher / creator: Imagine Art
Description: Imagine Art's high-fidelity native 4K model with lifelike realism, and refined aesthetics
Cost: 14 credits per image (~$0.0658)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:1, 1:3, 3:2, 2:3
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 3:1, 1:3, 3:2, 2:3. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "imagine-art-1-5-pro-full",
      "type": "image",
      "model": "imagine-art-1-5-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "imagine-art-1-5-pro-example",
      "type": "image",
      "model": "imagine-art-1-5-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Volt

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Volt
Model name to send: volt
Request type: image
Publisher / creator: imgnAI
Description: Anime style characters with a retro palette.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "volt-full",
      "type": "image",
      "model": "volt",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "volt-example",
      "type": "image",
      "model": "volt",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.7 Image

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.7 Image
Model name to send: wan-2-7-image
Request type: image
Publisher / creator: Alibaba
Description: Alibaba's Base WAN 2.7 Image model, bringing WAN's signature best-in-class natural realism at a budget cost!
Cost: 6 credits per image (~$0.0282)
Supported aspects: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 9
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 3:4, 4:3, 1:8, 8:1, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 9 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "wan-2-7-image-full",
      "type": "image",
      "model": "wan-2-7-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "wan-2-7-image-example",
      "type": "image",
      "model": "wan-2-7-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: GPT Image 1.5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: GPT Image 1.5
Model name to send: gpt-image-1-5
Request type: image
Publisher / creator: OpenAI
Description: OpenAI's flagship image model.
Cost: 32 credits per image (~$0.1504)
Supported aspects: 1:1
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "gpt-image-1-5-full",
      "type": "image",
      "model": "gpt-image-1-5",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "gpt-image-1-5-example",
      "type": "image",
      "model": "gpt-image-1-5",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Muse

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Muse
Model name to send: muse
Request type: image
Publisher / creator: imgnAI
Description: Flux-based model fine-tuned on Goths, Emos, and e-girls. Yes, really.
Cost: 3 credits per image (~$0.0141)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "muse-full",
      "type": "image",
      "model": "muse",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "muse-example",
      "type": "image",
      "model": "muse",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FLUX.2 PRO

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FLUX.2 PRO
Model name to send: flux-2-pro
Request type: image
Publisher / creator: Black Forest Labs
Description: FLUX.2's entry-level model, offering great performance at budget pricing.
Cost: 8 credits per image (~$0.0376)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9
Supported input types: not listed
Reference Images Supported: 4
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 4 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-2-pro-full",
      "type": "image",
      "model": "flux-2-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-2-pro-example",
      "type": "image",
      "model": "flux-2-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Gothic

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Gothic
Model name to send: gothic
Request type: image
Publisher / creator: imgnAI
Description: Dark clothes, dark hair, dark eyeliner. All the best things in an image model.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "gothic-full",
      "type": "image",
      "model": "gothic",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "gothic-example",
      "type": "image",
      "model": "gothic",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Z-Image Base

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Z-Image Base
Model name to send: z-image-base
Request type: image
Publisher / creator: Z.ai
Description: Z.ai's foundational image model, built for high quality and generative diversity at budget pricing.
Cost: 7 credits per image (~$0.0329)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "z-image-base-full",
      "type": "image",
      "model": "z-image-base",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "z-image-base-example",
      "type": "image",
      "model": "z-image-base",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Z-Image Turbo

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Z-Image Turbo
Model name to send: z-image-turbo
Request type: image
Publisher / creator: Z.ai
Description: Z.ai's Turbo image model, a lightning-fast distillation of Z-Image Base.
Cost: 4 credits per image (~$0.0188)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "z-image-turbo-full",
      "type": "image",
      "model": "z-image-turbo",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "z-image-turbo-example",
      "type": "image",
      "model": "z-image-turbo",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Rend

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Rend
Model name to send: rend
Request type: image
Publisher / creator: imgnAI
Description: A high-quality blended mix of path-traced rendering, and anime stylization.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "rend-full",
      "type": "image",
      "model": "rend",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "rend-example",
      "type": "image",
      "model": "rend",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Retro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Retro
Model name to send: retro
Request type: image
Publisher / creator: imgnAI
Description: Retro-styled anime, straight from the 90's!
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "retro-full",
      "type": "image",
      "model": "retro",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "retro-example",
      "type": "image",
      "model": "retro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FLUX.2 Klein 4b

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FLUX.2 Klein 4b
Model name to send: flux-2-klein-4b
Request type: image
Publisher / creator: Black Forest Labs
Description: FLUX.2's small but powerful Klein 4b model, further extending the cost savings offered with Klein 9b.
Cost: 4 credits per image (~$0.0188)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5
Supported input types: not listed
Reference Images Supported: 4
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 4:7, 7:4, 5:2, 2:5. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 4 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-2-klein-4b-full",
      "type": "image",
      "model": "flux-2-klein-4b",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-2-klein-4b-example",
      "type": "image",
      "model": "flux-2-klein-4b",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Neo

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Neo
Model name to send: neo
Request type: image
Publisher / creator: imgnAI
Description: High quality realism & render model optimized for UHD Mode.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "neo-full",
      "type": "image",
      "model": "neo",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "neo-example",
      "type": "image",
      "model": "neo",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Pony

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Pony
Model name to send: pony
Request type: image
Publisher / creator: imgnAI
Description: Expressive sketch-like anime model with excellent character recognition.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "pony-full",
      "type": "image",
      "model": "pony",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "pony-example",
      "type": "image",
      "model": "pony",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Nai

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Nai
Model name to send: nai
Request type: image
Publisher / creator: imgnAI
Description: Modern, alternative anime style model.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "nai-full",
      "type": "image",
      "model": "nai",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "nai-example",
      "type": "image",
      "model": "nai",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FLUX 1.1 Ultra

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FLUX 1.1 Ultra
Model name to send: flux-1-1-ultra
Request type: image
Publisher / creator: Black Forest Labs
Description: BFL's final FLUX.1 iteration, extremely high quality 4MP outputs.
Cost: 18 credits per image (~$0.0846)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-1-1-ultra-full",
      "type": "image",
      "model": "flux-1-1-ultra",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-1-1-ultra-example",
      "type": "image",
      "model": "flux-1-1-ultra",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Glitch

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Glitch
Model name to send: glitch
Request type: image
Publisher / creator: imgnAI
Description: Load up on glitch-burn aesthetics, with this compelling and unique art style!
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "glitch-full",
      "type": "image",
      "model": "glitch",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "glitch-example",
      "type": "image",
      "model": "glitch",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Qwen Image

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen Image
Model name to send: qwen-image
Request type: image
Publisher / creator: Alibaba Cloud
Description: Versatile model with excellent text capabilities.
Cost: 8 credits per image (~$0.0376)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "qwen-image-full",
      "type": "image",
      "model": "qwen-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "qwen-image-example",
      "type": "image",
      "model": "qwen-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Seedream 4

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedream 4
Model name to send: seedream-4
Request type: image
Publisher / creator: ByteDance
Description: Excellent quality 4K model, with full edit capabilities.
Cost: 12 credits per image (~$0.0564)
Supported aspects: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
Supported input types: not listed
Reference Images Supported: 10
User-facing capabilities: Supports Reference Images, Edit workflow, Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Optional. Provide an image URL, data URL, or raw base64 image string in image_urls for edit/reference workflows. input_images is accepted as an alias.
- Reference images: Supported. Provide up to 10 image URL(s), data URL(s), or raw base64 image string(s) in image_urls or reference_assets.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "seedream-4-full",
      "type": "image",
      "model": "seedream-4",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ],
      "reference_assets": [
        {
          "kind": "style_reference",
          "url": "https://example.com/reference.png"
        }
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "seedream-4-example",
      "type": "image",
      "model": "seedream-4",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.2 Image

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.2 Image
Model name to send: wan-2-2-image
Request type: image
Publisher / creator: Alibaba Cloud
Description: Stunning still-frame imagery powered by the WAN Video model.
Cost: 8 credits per image (~$0.0376)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "wan-2-2-image-full",
      "type": "image",
      "model": "wan-2-2-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "wan-2-2-image-example",
      "type": "image",
      "model": "wan-2-2-image",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Flux1.D

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Flux1.D
Model name to send: flux1-d
Request type: image
Publisher / creator: Black Forest Labs
Description: BFL's general-purpose Flux1.D model.
Cost: 3 credits per image (~$0.0141)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Natural language

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux1-d-full",
      "type": "image",
      "model": "flux1-d",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux1-d-example",
      "type": "image",
      "model": "flux1-d",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Qwen Image Edit

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Qwen Image Edit
Model name to send: qwen-image-edit
Request type: image
Publisher / creator: Alibaba Cloud
Description: Super-charged Qwen Image, with full image editing capabilities.
Cost: 12 credits per image (~$0.0564)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Edit workflow, Natural language, Requires image

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Required. Provide an image URL, data URL, or raw base64 image string in image_urls. input_images is accepted as an alias.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "qwen-image-edit-full",
      "type": "image",
      "model": "qwen-image-edit",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "qwen-image-edit-example",
      "type": "image",
      "model": "qwen-image-edit",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Supra

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Supra
Model name to send: supra
Request type: image
Publisher / creator: imgnAI
Description: Digital render style model, similar to MidJourney v6.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "supra-full",
      "type": "image",
      "model": "supra",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "supra-example",
      "type": "image",
      "model": "supra",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Evo

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Evo
Model name to send: evo
Request type: image
Publisher / creator: imgnAI
Description: Slightly abstract realism, flexible model specializing in texture details.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "evo-full",
      "type": "image",
      "model": "evo",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "evo-example",
      "type": "image",
      "model": "evo",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Toon

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Toon
Model name to send: toon
Request type: image
Publisher / creator: imgnAI
Description: Western cartoon style model.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "toon-full",
      "type": "image",
      "model": "toon",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "toon-example",
      "type": "image",
      "model": "toon",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Wassie

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Wassie
Model name to send: wassie
Request type: image
Publisher / creator: imgnAI
Description: Create Wassies of all shapes and sizes!
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "wassie-full",
      "type": "image",
      "model": "wassie",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "wassie-example",
      "type": "image",
      "model": "wassie",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: HyperX

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: HyperX
Model name to send: hyperx
Request type: image
Publisher / creator: imgnAI
Description: Legacy CG-Style renders.
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "hyperx-full",
      "type": "image",
      "model": "hyperx",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "hyperx-example",
      "type": "image",
      "model": "hyperx",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: FurXL Classic

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: FurXL Classic
Model name to send: furxl-classic
Request type: image
Publisher / creator: imgnAI
Description: Furries in all shapes and sizes!
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "furxl-classic-full",
      "type": "image",
      "model": "furxl-classic",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "furxl-classic-example",
      "type": "image",
      "model": "furxl-classic",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Flux Kontext Max

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Flux Kontext Max
Model name to send: flux-kontext-max
Request type: image
Publisher / creator: Black Forest Labs
Description: BFL's legacy high-end image editing model.
Cost: 20 credits per image (~$0.0940)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Edit workflow, Natural language, Requires image

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Required. Provide an image URL, data URL, or raw base64 image string in image_urls. input_images is accepted as an alias.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-kontext-max-full",
      "type": "image",
      "model": "flux-kontext-max",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-kontext-max-example",
      "type": "image",
      "model": "flux-kontext-max",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Flux Kontext Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Flux Kontext Pro
Model name to send: flux-kontext-pro
Request type: image
Publisher / creator: Black Forest Labs
Description: BFL's legacy entry-level image editing model.
Cost: 12 credits per image (~$0.0564)
Supported aspects: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Edit workflow, Natural language, Requires image

## Request fields and behavior

- prompt: Required. Write a natural-language image instruction.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Source image: Required. Provide an image URL, data URL, or raw base64 image string in image_urls. input_images is accepted as an alias.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "flux-kontext-pro-full",
      "type": "image",
      "model": "flux-kontext-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "image_urls": [
        "https://example.com/source-or-reference.png"
      ]
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "flux-kontext-pro-example",
      "type": "image",
      "model": "flux-kontext-pro",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "image_urls": [
        "https://example.com/source.png"
      ]
    }
  ]
}
```

# imgnAI model integration guide: Supra Classic

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Supra Classic
Model name to send: supra-classic
Request type: image
Publisher / creator: imgnAI
Description: High-range Digital Renders
Cost: 2 credits per image (~$0.0094)
Supported aspects: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: Booru tag prompting

## Request fields and behavior

- prompt: Required. This model is tag-prompt oriented; comma-separated booru-style tags usually work best.
- negative_prompt: Optional. If omitted, the model default negative prompt is used where one exists.
- aspect_ratio: Required unless width and height are provided. Supported: 1:1, 16:9, 21:9, 3:4, 9:16, 5:2, 4:3, 5:4, 4:5, 9:21, 4:7. AUTO can inspect the first input image and choose the closest supported ratio; with no input it defaults to 1:1 when supported.
- output_format: Optional. Supported values: png, jpeg, webp. jpg is accepted as an alias for jpeg.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- Hosted resolution modes: Supported on this imgnAI-hosted model: `is_fast`/`fast_mode` for lower-cost half-resolution generation; `is_uhd`/`uhd_mode` for UHD generation. If both are sent, UHD takes precedence.
- Prompt assist: Allows natural-language prompts on this tag/booru-based model by translating user prose into tag-style prompts before dispatch. Send use_assistant, prompt_assist, or use_prompt_assist.
- Attachments: Optional single source image accepted for compatible workflows; text-only generation is the default.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-image-full-options",
  "requests": [
    {
      "id": "supra-classic-full",
      "type": "image",
      "model": "supra-classic",
      "prompt": "ceramic mug, table, clean product photo, soft light",
      "negative_prompt": "low quality, blurry",
      "aspect_ratio": "1:1",
      "output_format": "png",
      "width": null,
      "height": null,
      "seed": 123456,
      "metadata": {
        "source": "api-docs"
      },
      "is_fast": false,
      "fast_mode": false,
      "is_uhd": false,
      "uhd_mode": false,
      "use_assistant": false,
      "prompt_assist": false,
      "use_prompt_assist": false
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-image-example",
  "requests": [
    {
      "id": "supra-classic-example",
      "type": "image",
      "model": "supra-classic",
      "prompt": "A clean product image of a ceramic mug on a table",
      "aspect_ratio": "1:1",
      "output_format": "png"
    }
  ]
}
```

# imgnAI model integration guide: Seedance 2.0

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance 2.0
Model name to send: seedance-2-0
Request type: video
Publisher / creator: ByteDance
Description: The world's frontier video model, offering unprecedented prompt adherence and audio/video quality.
Cost: 5 seconds: 200 credits (~$0.9400); 10 seconds: 375 credits (~$1.76); 15 seconds: 550 credits (~$2.58)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 7
User-facing capabilities: First frame, Last frame, Supports Reference Images, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 7 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.
- Audio references: Supported. Provide up to 3 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Reference images cannot be combined with first-frame or last-frame inputs.
- Audio input cannot be combined with first-frame or last-frame inputs.
- Last-frame input requires a first-frame input.
- Combined selected audio input is limited to 15 seconds.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-2-0-full",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        },
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-2-0-example",
      "type": "video",
      "model": "seedance-2-0",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Seedance 2.0 (480p)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance 2.0 (480p)
Model name to send: seedance-2-0-480p
Request type: video
Publisher / creator: ByteDance
Description: All the power of Seedance 2.0's full model - optimized for Mobile resolutions, at half the cost!
Cost: 5 seconds: 120 credits (~$0.5640); 10 seconds: 230 credits (~$1.08); 15 seconds: 340 credits (~$1.60)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 7
User-facing capabilities: First frame, Last frame, Supports Reference Images, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 7 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.
- Audio references: Supported. Provide up to 3 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Reference images cannot be combined with first-frame or last-frame inputs.
- Audio input cannot be combined with first-frame or last-frame inputs.
- Last-frame input requires a first-frame input.
- Combined selected audio input is limited to 15 seconds.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-2-0-480p-full",
      "type": "video",
      "model": "seedance-2-0-480p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        },
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-2-0-480p-example",
      "type": "video",
      "model": "seedance-2-0-480p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Seedance 2.0 (Fast)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance 2.0 (Fast)
Model name to send: seedance-2-0-fast
Request type: video
Publisher / creator: ByteDance
Description: Seedance 2.0's Fast model, offering a powerful budget entry for full resolution outputs!
Cost: 5 seconds: 120 credits (~$0.5640); 10 seconds: 230 credits (~$1.08); 15 seconds: 340 credits (~$1.60)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 7
User-facing capabilities: First frame, Last frame, Supports Reference Images, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 7 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.
- Audio references: Supported. Provide up to 3 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Reference images cannot be combined with first-frame or last-frame inputs.
- Audio input cannot be combined with first-frame or last-frame inputs.
- Last-frame input requires a first-frame input.
- Combined selected audio input is limited to 15 seconds.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-2-0-fast-full",
      "type": "video",
      "model": "seedance-2-0-fast",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        },
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-2-0-fast-example",
      "type": "video",
      "model": "seedance-2-0-fast",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: LTX 2.3

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: LTX 2.3
Model name to send: ltx-2-3
Request type: video
Publisher / creator: Lightricks
Description: Powerful open source audio-video model by Lightricks - hosted in-house for premium results at dramatically lower prices.
Cost: 5 seconds: 20 credits (~$0.0940); 10 seconds: 40 credits (~$0.1880); 15 seconds: 60 credits (~$0.2820); 20 seconds: 80 credits (~$0.3760)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Last frame, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15, 20. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Audio references: Supported. Provide up to 1 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Audio input can only be used with first-frame conditioning.
- Video duration follows the selected audio duration.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "ltx-2-3-full",
      "type": "video",
      "model": "ltx-2-3",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "ltx-2-3-example",
      "type": "video",
      "model": "ltx-2-3",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Happy Horse 1.0 (1080p)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Happy Horse 1.0 (1080p)
Model name to send: happy-horse-1-0-1080p
Request type: video
Publisher / creator: Alibaba
Description: Alibaba's newest frontier model; boasts breathtaking quality and prompt adherence, at full 1080p resolutions.
Cost: 5 seconds: 300 credits (~$1.41); 10 seconds: 600 credits (~$2.82); 15 seconds: 900 credits (~$4.23)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 9
User-facing capabilities: First frame, Supports Reference Images

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, reference images. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 9 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.

## Custom media rules

- Reference images cannot be combined with first-frame or last-frame inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "happy-horse-1-0-1080p-full",
      "type": "video",
      "model": "happy-horse-1-0-1080p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": []
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "happy-horse-1-0-1080p-example",
      "type": "video",
      "model": "happy-horse-1-0-1080p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Happy Horse 1.0 (720p)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Happy Horse 1.0 (720p)
Model name to send: happy-horse-1-0-720p
Request type: video
Publisher / creator: Alibaba
Description: Alibaba's powerful Happy Horse 1.0 model - retaining breathtaking quality at 720p resolutions, coupled with discounted pricing!
Cost: 5 seconds: 150 credits (~$0.7050); 10 seconds: 300 credits (~$1.41); 15 seconds: 450 credits (~$2.12)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 9
User-facing capabilities: First frame, Supports Reference Images

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, reference images. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 9 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.

## Custom media rules

- Reference images cannot be combined with first-frame or last-frame inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "happy-horse-1-0-720p-full",
      "type": "video",
      "model": "happy-horse-1-0-720p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": []
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "happy-horse-1-0-720p-example",
      "type": "video",
      "model": "happy-horse-1-0-720p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.7 (1080p)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.7 (1080p)
Model name to send: wan-2-7-1080p
Request type: video
Publisher / creator: Alibaba
Description: WAN 2.7 excels in creating videos with breathtaking consistency across reference images, and high-fidelity textures.
Cost: 5 seconds: 130 credits (~$0.6110); 10 seconds: 260 credits (~$1.22)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 5
User-facing capabilities: First frame, Last frame, Supports Reference Images, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 5 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.
- Audio references: Supported. Provide up to 1 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Reference audio is interpreted as voice timbre when reference images are present.
- Reference images cannot be combined with first-frame or last-frame inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "wan-2-7-1080p-full",
      "type": "video",
      "model": "wan-2-7-1080p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        },
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "wan-2-7-1080p-example",
      "type": "video",
      "model": "wan-2-7-1080p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.7 (720p)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.7 (720p)
Model name to send: wan-2-7-720p
Request type: video
Publisher / creator: Alibaba
Description: Alibaba's 720p WAN 2.7 model - retaining excellent quality, at a discounted rate!
Cost: 5 seconds: 90 credits (~$0.4230); 10 seconds: 180 credits (~$0.8460)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 5
User-facing capabilities: First frame, Last frame, Supports Reference Images, Audio references

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images, audio references. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 5 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.
- Audio references: Supported. Provide up to 1 audio reference file(s) in video_image_data.audio_input_urls.

## Custom media rules

- Reference audio is interpreted as voice timbre when reference images are present.
- Reference images cannot be combined with first-frame or last-frame inputs.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "wan-2-7-720p-full",
      "type": "video",
      "model": "wan-2-7-720p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": [
          "https://example.com/reference-audio.mp3"
        ]
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        },
        {
          "kind": "reference_audio",
          "url": "https://example.com/reference-audio.mp3"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "wan-2-7-720p-example",
      "type": "video",
      "model": "wan-2-7-720p",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Kling O3 4K

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling O3 4K
Model name to send: kling-o3-4k
Request type: video
Publisher / creator: Kling AI
Description: Kling's flagship O3 model, in astonishing 4K Quality!
Cost: 5 seconds: 450 credits (~$2.12); 10 seconds: 900 credits (~$4.23); 15 seconds: 1350 credits (~$6.35)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 6
User-facing capabilities: First frame, Last frame, Supports Reference Images

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 6 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-o3-4k-full",
      "type": "video",
      "model": "kling-o3-4k",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": []
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-o3-4k-example",
      "type": "video",
      "model": "kling-o3-4k",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/reference.png"
        ]
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 3.0

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 3.0
Model name to send: kling-3-0-kling30pro
Request type: video
Publisher / creator: Kling AI
Description: Kling's flagship 3.0 model, pairing excellent prompt adherence with industry quality audio/video output.
Cost: 5 seconds: 350 credits (~$1.65); 10 seconds: 650 credits (~$3.06); 15 seconds: 925 credits (~$4.35)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 6
User-facing capabilities: First frame, Last frame, Supports Reference Images

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 6 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-3-0-kling30pro-full",
      "type": "video",
      "model": "kling-3-0-kling30pro",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": []
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-3-0-kling30pro-example",
      "type": "video",
      "model": "kling-3-0-kling30pro",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/reference.png"
        ]
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 3.0

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 3.0
Model name to send: kling-3-0-kling30
Request type: video
Publisher / creator: Kling AI
Description: Kling's cutting-edge 3.0 model, with great prompt adherence, and stellar quality audio/video output.
Cost: 5 seconds: 280 credits (~$1.32); 10 seconds: 550 credits (~$2.58); 15 seconds: 800 credits (~$3.76)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 6
User-facing capabilities: First frame, Last frame, Supports Reference Images

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10, 15. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame, last frame, reference images. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Last frame image: Supported in video_image_data.last_frame_image_url. Use an image URL, data URL, or raw base64 image string.
- Reference images: Supported. Provide up to 6 image URL(s), data URL(s), or raw base64 image string(s) in video_image_data.reference_image_urls.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-3-0-kling30-full",
      "type": "video",
      "model": "kling-3-0-kling30",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": "https://example.com/last-frame.png",
        "reference_image_urls": [
          "https://example.com/reference.png"
        ],
        "audio_input_urls": []
      },
      "reference_assets": [
        {
          "kind": "reference_image",
          "url": "https://example.com/reference.png"
        }
      ],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-3-0-kling30-example",
      "type": "video",
      "model": "kling-3-0-kling30",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "reference_image_urls": [
          "https://example.com/reference.png"
        ]
      }
    }
  ]
}
```

# imgnAI model integration guide: Veo3.1

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Veo3.1
Model name to send: veo3-1
Request type: video
Publisher / creator: Google
Description: Google's updated Veo3.1 model, showcasing 1080p cinematic quality video, with full audio support.
Cost: 4 seconds: 380 credits (~$1.79); 8 seconds: 750 credits (~$3.53)
Supported aspects: 16:9, 9:16
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 4, 8. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "veo3-1-full",
      "type": "video",
      "model": "veo3-1",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 4,
      "seconds": 4,
      "duration": "4s",
      "num_frames": 65,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "veo3-1-example",
      "type": "video",
      "model": "veo3-1",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 4,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Veo3.1 Fast

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Veo3.1 Fast
Model name to send: veo3-1-fast
Request type: video
Publisher / creator: Google
Description: Veo 3.1's little brother - bringing high speeds at lower costs, while still offering superb quality audio/video generation.
Cost: 4 seconds: 160 credits (~$0.7520); 8 seconds: 300 credits (~$1.41)
Supported aspects: 16:9, 9:16
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 4, 8. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "veo3-1-fast-full",
      "type": "video",
      "model": "veo3-1-fast",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 4,
      "seconds": 4,
      "duration": "4s",
      "num_frames": 65,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "veo3-1-fast-example",
      "type": "video",
      "model": "veo3-1-fast",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 4,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Veo3.1 Lite

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Veo3.1 Lite
Model name to send: veo3-1-lite
Request type: video
Publisher / creator: Google
Description: Google's latest offering in their Veo3.1 line, packing excellent quality at an incredibly low cost!
Cost: 8 seconds: 140 credits (~$0.6580)
Supported aspects: 16:9, 9:16
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 8. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "veo3-1-lite-full",
      "type": "video",
      "model": "veo3-1-lite",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 8,
      "seconds": 8,
      "duration": "8s",
      "num_frames": 129,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "veo3-1-lite-example",
      "type": "video",
      "model": "veo3-1-lite",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 8,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Seedance Pro

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance Pro
Model name to send: seedance-pro
Request type: video
Publisher / creator: ByteDance
Description: Excellent quality HD outputs across a range of styles, with excellent prompt adherence.
Cost: 5 seconds: 250 credits (~$1.18); 10 seconds: 450 credits (~$2.12)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-pro-full",
      "type": "video",
      "model": "seedance-pro",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-pro-example",
      "type": "video",
      "model": "seedance-pro",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: WAN 2.5

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: WAN 2.5
Model name to send: wan-2-5
Request type: video
Publisher / creator: Alibaba Cloud
Description: Excellent quality HD outputs with full audio generation, at a stunningly low cost.
Cost: 5 seconds: 220 credits (~$1.03); 10 seconds: 400 credits (~$1.88)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "wan-2-5-full",
      "type": "video",
      "model": "wan-2-5",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "wan-2-5-example",
      "type": "video",
      "model": "wan-2-5",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9"
    }
  ]
}
```

# imgnAI model integration guide: Hailuo 2 (MiniMax)

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Hailuo 2 (MiniMax)
Model name to send: hailuo-2-minimax
Request type: video
Publisher / creator: Hailuo AI
Description: Great quality at competitive pricing, excels at text rendering.
Cost: 6 seconds: 200 credits (~$0.9400)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 6. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "hailuo-2-minimax-full",
      "type": "video",
      "model": "hailuo-2-minimax",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 6,
      "seconds": 6,
      "duration": "6s",
      "num_frames": 97,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "hailuo-2-minimax-example",
      "type": "video",
      "model": "hailuo-2-minimax",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 6,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 2.1

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 2.1
Model name to send: kling-2-1-kling21
Request type: video
Publisher / creator: Kling AI
Description: Quality close to Kling's master 2.0 model, at budget pricing.
Cost: 5 seconds: 160 credits (~$0.7520); 10 seconds: 300 credits (~$1.41)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-2-1-kling21-full",
      "type": "video",
      "model": "kling-2-1-kling21",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-2-1-kling21-example",
      "type": "video",
      "model": "kling-2-1-kling21",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 2.1

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 2.1
Model name to send: kling-2-1-kling21loop
Request type: video
Publisher / creator: Kling AI
Description: Infinitely looped videos with Kling 2.1!
Cost: 5 seconds: 160 credits (~$0.7520); 10 seconds: 300 credits (~$1.41)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-2-1-kling21loop-full",
      "type": "video",
      "model": "kling-2-1-kling21loop",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-2-1-kling21loop-example",
      "type": "video",
      "model": "kling-2-1-kling21loop",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Seedance Lite

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance Lite
Model name to send: seedance-lite-seedancelite
Request type: video
Publisher / creator: ByteDance
Description: Exceptional cost-to-performance video model.
Cost: 5 seconds: 120 credits (~$0.5640); 10 seconds: 200 credits (~$0.9400)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-lite-seedancelite-full",
      "type": "video",
      "model": "seedance-lite-seedancelite",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-lite-seedancelite-example",
      "type": "video",
      "model": "seedance-lite-seedancelite",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Seedance Lite

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Seedance Lite
Model name to send: seedance-lite-seedanceliteloop
Request type: video
Publisher / creator: ByteDance
Description: Infinitely looped videos with Seedance Lite!
Cost: 5 seconds: 120 credits (~$0.5640); 10 seconds: 200 credits (~$0.9400)
Supported aspects: 16:9, 9:16, 1:1, 4:3, 3:4
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1, 4:3, 3:4. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "seedance-lite-seedanceliteloop-full",
      "type": "video",
      "model": "seedance-lite-seedanceliteloop",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "seedance-lite-seedanceliteloop-example",
      "type": "video",
      "model": "seedance-lite-seedanceliteloop",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 2.0

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 2.0
Model name to send: kling-2-0
Request type: video
Publisher / creator: Kling AI
Description: Kling's raw/master 2.0 video model. Excellent quality, but very highly priced for video-only.
Cost: 5 seconds: 350 credits (~$1.65); 10 seconds: 650 credits (~$3.06)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-2-0-full",
      "type": "video",
      "model": "kling-2-0",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-2-0-example",
      "type": "video",
      "model": "kling-2-0",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```

# imgnAI model integration guide: Kling 1.6

This document is self-contained. Use it to call the live imgnAI API with no other context.

## Endpoint and authentication

Base URL: http://devkat.imgnai.com
Create or view API keys: https://app.imgnai.com/api
Purchase credits and subscriptions: https://app.imgnai.com
Text models use POST /v1/chat/completions. Image and video models use POST /v1/generation-requests?wait=true.
Text requests accept OpenAI-style messages, a single prompt fallback when messages is omitted, and stream: true Server-Sent Events.
Text responses include usage.imgnai with reserved credits, final charged credits, refunds, privacy mode, billing source, and the public model name.
For image/video async behavior, POST /v1/generation-requests?wait=false returns quickly; poll GET /v1/generation-requests/{request_id}.
Required headers:

```http
Content-Type: application/json
Authorization: Bearer <api_key>:<api_secret>   # text/OpenAI-compatible clients
X-API-Key: <api_key>                           # image/video clients
X-API-Secret: <secret_key>                      # image/video clients
```

x402 alternative:

```http
PAYMENT-SIGNATURE: <base64-json-signed-x402-payment>
```

To use x402, send the same request once without credentials, read the `402 Payment Required` response and Base64 JSON `PAYMENT-REQUIRED` header, choose the Base or Solana USDC `accepts` entry, sign/pay it with an x402-compatible client, then retry with `PAYMENT-SIGNATURE`. Base (`eip155:8453`) is the default recommended network. imgnAI verifies and settles payment before starting inference.

x402 zero-context payment summary:

- x402 lets a user call this model without an API key by paying exact USDC for a single request.
- First send the ordinary request without API credentials. imgnAI returns HTTP 402 and a Base64 JSON `PAYMENT-REQUIRED` header.
- Decode `PAYMENT-REQUIRED`, choose either Base USDC (`eip155:8453`) or Solana USDC (`solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp`), and do not edit the selected amount, asset, network, or payTo fields.
- Gas is included in the USDC amount, so the selected `amount` / `maxAmountRequired` covers both the model price and imgnAI's settlement transaction cost.
- Base payments use an EIP-3009-style USDC `transferWithAuthorization` signed as EIP-712 typed data. Encode the payment JSON as Base64 and send it as `PAYMENT-SIGNATURE`.
- Solana payments use a customer-signed, Base64 serialized VersionedTransaction that transfers exact USDC to the imgnAI payTo token account. imgnAI validates it, co-signs the oracle fee payer, broadcasts it, and only then starts inference.
- Retry the exact same endpoint and JSON body with `PAYMENT-SIGNATURE`. Successful paid responses include `PAYMENT-RESPONSE`, a Base64 JSON receipt.
- Full x402 examples for image, video, and text on both networks are available from `http://devkat.imgnai.com/llms.txt` under `x402 Zero-Context Integration Guide`.

## Selected model

Display name: Kling 1.6
Model name to send: kling-1-6
Request type: video
Publisher / creator: Kling AI
Description: [Legacy] Kling's early-era 1.6 video generation model.
Cost: 5 seconds: 130 credits (~$0.6110); 10 seconds: 250 credits (~$1.18)
Supported aspects: 16:9, 9:16, 1:1
Supported input types: not listed
Reference Images Supported: 0
User-facing capabilities: First frame, Silent/No Audio, Requires image

## Request fields and behavior

- prompt: Required. Describe the intended motion, camera behavior, subject, and scene.
- negative_prompt: Optional. Avoid using it unless the target model meaningfully responds to negative prompting.
- duration_seconds: Use one of this model's configured durations: 5, 10. The aliases seconds, duration, or compatible num_frames can also resolve a duration.
- aspect_ratio: Use a value from supported_aspects: 16:9, 9:16, 1:1. AUTO uses the first frame image, then the first reference image; with no media it defaults to 1:1 when supported.
- seed: Optional integer. Reusing the same seed helps repeat similar results.
- video_image_data: Use this object only for this model's supported media slots: first frame. Generic image_url/input_image_url is treated as first_frame_image_url for compatible first-frame models.
- Input requirement: This model requires an image input. Use a supported frame slot.
- First frame image: Supported in video_image_data.first_frame_image_url. Use an image URL, data URL, or raw base64 image string.

## Full option sample

The sample includes the fields an integration should know about. Omit unsupported media fields and null placeholders for the selected model before sending.

```json
{
  "client_request_id": "client-video-full-options",
  "requests": [
    {
      "id": "kling-1-6-full",
      "type": "video",
      "model": "kling-1-6",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "negative_prompt": "",
      "duration_seconds": 5,
      "seconds": 5,
      "duration": "5s",
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "width": null,
      "height": null,
      "seed": 123456,
      "input_image_url": "https://example.com/first-frame.png",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png",
        "mid_frame_image_url": null,
        "last_frame_image_url": null,
        "reference_image_urls": [],
        "audio_input_urls": []
      },
      "reference_assets": [],
      "metadata": {
        "source": "api-docs"
      }
    }
  ]
}
```

## Minimal practical sample

```json
{
  "client_request_id": "client-video-example",
  "requests": [
    {
      "id": "kling-1-6-example",
      "type": "video",
      "model": "kling-1-6",
      "prompt": "A calm cinematic shot of a ceramic mug on a table",
      "duration_seconds": 5,
      "aspect_ratio": "16:9",
      "video_image_data": {
        "first_frame_image_url": "https://example.com/first-frame.png"
      }
    }
  ]
}
```