Image generation over the standard `POST /v1/chat/completions` route using OpenAI's multimodal `content` array; AIsa returns `choices[].message.content[]` containing one or more `{type: "image"}` parts. **As of July 28, 2026 the Wan 2.7 image models have moved to `/v1/images/generations` and `/v1/images/edits`** — `seedream-4-5-251128` is the remaining model configured on this route.
About Image Generation via Chat Completions via AIsa
Review the Service identity, supported languages, protocol versions, and source metadata discovered by the directory.
Service details
Service Id
0368a1f7-e2fb-452e-a2fc-8019227378bc
Service origin
https://api.aisa.one
ListedSeptember 24, 2026, 6:37 PM
Last checkedSeptember 24, 2026, 7:57 PM
Protocol details
SourceOpenAPI
Endpoints
Endpoint details are saved from the OpenAPI document. Authentication requirements and prices are advertised information, not a verified payment or access guarantee. The document may contain additional endpoints.Open OpenAPI document
POST/chat/completions
Generate images via Chat Completions
Generate images over the chat route. Request shape matches OpenAI Chat Completions with multimodal content; the response contains `choices[].message.content[]` where each item is `{type: "image", image: "<url or base64>"}`.
**Important:** `messages[].content` must be an **array of typed parts**, not a plain string. Passing a string returns `400 invalid_parameter_error` with `Input should be a valid list: messages[*].content`.
**Routing note:** `wan2.7-image`, `wan2.7-image-pro`, `seedream-5-0-260128`, and `gpt-image-2` return `400 model_route_not_supported` here — use `/v1/images/generations` for those.Price unavailableThe operation requires declared authentication; API keys, bearer tokens and other schemes are not evidence of AEP support.