Skip to main content
POST
LLM placeholder / LLM 接口预留
API preview: generation providers are not connected. An authenticated request can return 503 without creating a task or charging credits.

Compatibility is per model

Chat Completions is the planned compatibility surface. Check messages, tools, structured output, vision, context limits, and usage support for the exact model. Do not infer complete OpenAI compatibility from the endpoint name. Real LLM providers are not connected in this build stage. The example documents the intended request; it must not return invented model text as a live completion.

Streaming changes recovery

  • Before visible content is sent, an eligible confirmed failure may use an authorized fallback.
  • After text, a tool call, or other visible SSE data is sent, do not restart on another supplier and concatenate a second answer.
  • A client disconnect is not automatically free. Record known usage and resolve unknown metering according to the model’s published contract.
  • Tools are instructions for your application. The platform must not repeat a tool action while recovering a stream.

Keep platform extensions explicit

If an SDK rejects custom fields such as fallback, use its supported extra-body mechanism or plain HTTP. Use only valid SDK options. The 1–4 image/video output_count field is not an LLM generation multiplier.

Authorizations

Authorization
string
header
required

API key beginning as_. Keep on the server. Scope permissions are checked separately.

Body

application/json

Planned payload only; live request validation is not yet connected.

The body is of type object.

Response

invalid_api_key

error
object
required