> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI-Compatible Image Generations > Generate images with Seedream, Wan, gpt-image-2, and GPT Image 2.5 via the standard POST /v1/images/generations endpoint. OpenAI-compatible request shape; Seedream routes require a minimum image size of 3,686,400 pixels (e.g., 1920×1920). The standard OpenAI-compatible `POST /v1/images/generations` endpoint. As of September 30, 2026 it serves `seedream-5-0-260128`, `wan2.7-image`, `wan2.7-image-pro`, `gpt-image-2`, `gpt-image-2.5-flare`, and `gpt-image-2.5-sunburst`. No image model is served on `POST /v1/chat/completions` — image generation goes through this endpoint (and `POST /v1/images/edits` where noted). ## Routing at a glance | Model | Endpoint | | - | - | | `seedream-5-0-260128` | **`POST /v1/images/generations`** *(this page)* | | `wan2.7-image` / `wan2.7-image-pro` | **`POST /v1/images/generations`** *(this page)*, `POST /v1/images/edits` | | `gpt-image-2` | **`POST /v1/images/generations`** *(this page)*, `POST /v1/images/edits` | | `gpt-image-2.5-flare` / `gpt-image-2.5-sunburst` | **`POST /v1/images/generations`** *(this page)*, `POST /v1/images/edits` | | Gemini-compatible models | [`POST /v1beta/models/{model}:generateContent`](/docs/api-reference/chat/post_models-model-generatecontent) | ## Supported models | Model | Billed by | Notes | | - | - | - | | `seedream-5-0-260128` | Per request | Min image size **3,686,400 pixels** (e.g., 1920×1920) | | `wan2.7-image` | Per request | Also accepts `POST /v1/images/edits` | | `wan2.7-image-pro` | Per request | Higher-quality Wan route | | `gpt-image-2` | Per request or per image; token pricing also applies on some routes | See [AI Model Pricing](/docs/guides/pricing/ai-model-pricing-llm-inference) | | `gpt-image-2.5-flare` | Per 1M tokens: input, output, cache read | GPT Image 2.5 route | | `gpt-image-2.5-sunburst` | Per 1M tokens: input, output, cache read | GPT Image 2.5 route | Current prices are on [aisa.one/models](https://aisa.one/models). ## Size constraint ⚠️ (Seedream routes) Seedream's upstream enforces a minimum of **3,686,400 pixels**. Requests below that are rejected with: ``` 400 InvalidParameter: image size must be at least 3686400 pixels ``` | Size | Pixels | Accepted? | | - | - | - | | `1024x1024` | 1,048,576 | ❌ | | `1536x1536` | 2,359,296 | ❌ | | `1920x1920` | 3,686,400 | ✅ (exact threshold) | | `2048x2048` | 4,194,304 | ✅ | | `2304x1600` | 3,686,400 | ✅ | | `2560x1920` | 4,915,200 | ✅ | Any aspect ratio works as long as `width × height ≥ 3,686,400`. ## Request ```bash curl theme={null} curl -sS -X POST "https://api.aisa.one/v1/images/generations" \ -H "Authorization: Bearer $AISA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "seedream-5-0-260128", "prompt": "A cute red panda, ultra-detailed, cinematic lighting", "n": 1, "size": "2048x2048" }' ``` ```python Python theme={null} from openai import OpenAI client = OpenAI(base_url="https://api.aisa.one/v1", api_key="sk-aisa-...") resp = client.images.generate( model="seedream-5-0-260128", prompt="A cute red panda, ultra-detailed, cinematic lighting", n=1, size="2048x2048", ) for item in resp.data: print(item.url) ``` ```typescript TypeScript theme={null} import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.aisa.one/v1", apiKey: process.env.AISA_API_KEY, }); const resp = await client.images.generate({ model: "seedream-5-0-260128", prompt: "A cute red panda, ultra-detailed, cinematic lighting", n: 1, size: "2048x2048", }); for (const item of resp.data) { console.log(item.url); } ``` ### Request fields | Field | Type | Required | Notes | | - | - | - | - | | `model` | string | yes | One of `seedream-5-0-260128`, `wan2.7-image`, `wan2.7-image-pro`, `gpt-image-2`, `gpt-image-2.5-flare`, `gpt-image-2.5-sunburst` | | `prompt` | string | yes | Text description of the image to generate | | `n` | integer | no | Number of images. Each is billed separately at the model's per-request rate | | `size` | string | no | `WIDTHxHEIGHT`. Seedream routes must satisfy `width × height ≥ 3,686,400`; `wan2.7-image` and `gpt-image-2` accept smaller sizes (`1024x1024` verified working) | ## Response ```json theme={null} { "model": "seedream-5-0-260128", "created": 1776495432, "data": [ { "url": "https://cdn.aisa.one/images/seedream/...", "size": "2048x2048" } ], "usage": { "generated_images": 1, "output_tokens": 16384, "total_tokens": 16384 } } ``` **AIsa's response adds a few extensions** over the vanilla OpenAI schema: * `model` echoed at the root * `data[].size` — actual dimensions of each returned image * `usage` — includes `generated_images` (drives billing), plus `output_tokens` / `total_tokens` for token accounting URLs in `data[].url` are **short-lived**. Download and persist the image to your own storage before it expires. ## Common 4xx causes * `400 InvalidParameter — image size must be at least 3686400 pixels` — `size` was too small. Use `1920x1920` or larger. * `400 model_route_not_supported` — the model doesn't serve this endpoint (e.g., a text model like `gpt-4.1-mini`). The error body's `supported_routes` lists the routes it does serve. * `404 model not found` — the model ID doesn't exist on the gateway (e.g., the retired `seedream-4-5-251128`). Check the [model catalog](/docs/guides/models). * `400 invalid_request` — malformed `size` string (e.g., `1024` instead of `1024x1024`). See [Error Codes](/docs/api-reference/errors) and [Rate Limits](/docs/api-reference/rate-limits) for more. ## Related Current model IDs and the endpoints each one serves. Gemini-compatible generateContent endpoint. Agent skill that wraps image + video generation. ## OpenAPI ````yaml openapi/openai-images-generations.json POST /images/generations openapi: 3.0.3 info: title: OpenAI-Compatible Image Generations version: 1.0.0 description: >- Standard OpenAI-compatible `POST /v1/images/generations` endpoint. As of September 30, 2026 it serves `seedream-5-0-260128`, `wan2.7-image`, `wan2.7-image-pro`, `gpt-image-2`, `gpt-image-2.5-flare`, and `gpt-image-2.5-sunburst`. No image model is served on `/v1/chat/completions`; Gemini-compatible `generateContent` requests use [`/v1beta/models/{model}:generateContent`](/api-reference/chat/post_models-model-generatecontent). servers: - url: https://api.aisa.one/v1 security: - BearerAuth: [] paths: /images/generations: post: summary: Generate images (OpenAI-compatible) description: >- Generate images with the OpenAI-compatible images-generations endpoint. **Size constraint (Seedream routes only).** Seedream's upstream requires a minimum of **3,686,400 pixels** per image. Requests below that return `400 InvalidParameter: image size must be at least 3686400 pixels`. Wan and `gpt-image-2` routes accept smaller sizes — `1024x1024` is verified working for `wan2.7-image`. operationId: createImageGeneration requestBody: required: true content: application/json: schema: type: object required: - model - prompt properties: model: type: string enum: - seedream-5-0-260128 - wan2.7-image - wan2.7-image-pro - gpt-image-2 - gpt-image-2.5-flare - gpt-image-2.5-sunburst description: >- Image generation model. `seedream-5-0-260128`, `wan2.7-image`, `wan2.7-image-pro`, `gpt-image-2`, `gpt-image-2.5-flare`, or `gpt-image-2.5-sunburst`. prompt: type: string description: Text description of the image to generate. 'n': type: integer minimum: 1 default: 1 description: >- Number of images to generate. Each image is billed separately at the per-image rate. size: type: string description: >- Image dimensions as `WIDTHxHEIGHT`. Seedream routes require `width × height ≥ 3,686,400` (e.g. `1920x1920`, `2048x2048`); Wan and `gpt-image-2` accept smaller sizes such as `1024x1024`. example: 2048x2048 examples: basic: summary: Single 2K image value: model: seedream-5-0-260128 prompt: A cute red panda, ultra-detailed, cinematic lighting 'n': 1 size: 2048x2048 minimum_size: summary: Exactly at minimum allowed size (1920×1920) value: model: seedream-5-0-260128 prompt: A futuristic cyberpunk city, neon lights, rainy night, 8k 'n': 1 size: 1920x1920 batch: summary: Four candidates for selection value: model: seedream-5-0-260128 prompt: Oil painting of a rolling hillside at sunset 'n': 4 size: 2048x2048 responses: '200': description: Images generated successfully. content: application/json: schema: type: object properties: model: type: string example: seedream-5-0-260128 created: type: integer example: 1776495432 data: type: array description: One entry per generated image. items: type: object properties: url: type: string format: uri description: >- Short-lived URL to the generated image. Download and persist it; the URL expires. size: type: string description: Actual dimensions of the returned image. usage: type: object properties: generated_images: type: integer output_tokens: type: integer total_tokens: type: integer example: model: seedream-5-0-260128 created: 1776495432 data: - url: https://cdn.aisa.one/images/seedream/20260418-abc.png size: 2048x2048 usage: generated_images: 1 output_tokens: 16384 total_tokens: 16384 '400': description: >- Invalid request. Most common: `size` smaller than 3,686,400 pixels → `"image size must be at least 3686400 pixels"`. '401': description: Missing or invalid AIsa API key. '404': description: >- The model isn't routed through this endpoint. The gateway returns `model_route_not_supported` with the model's actual supported routes — see the [model catalog](/guides/models). '429': description: Rate limit hit. '500': description: Internal error. '502': description: Upstream provider unreachable. components: securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: AISA API Key ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.