v1

latestOpenAPI 3.0.02026-07-1741634.0 KB

Inference

Run headless assistant orchestration with tool execution

Optionally loads assistant settings by assistant_id, executes server-side MCP tool calls, and continues generation until the model returns a final response.

post/orchestrations

Request body

assistant_idstring

Optional assistant id to load system prompt/model hint from

project_idstring nullable

Reserved for future parity; MCP-only execution currently

modelstring

Optional model override. If omitted, uses assistant's model hint or the first running local model.

streamboolean

Streaming is not supported for this endpoint.

max_turnsinteger

Maximum tool-calling turns before giving up.

Response

Completion result

idstring required

Unique identifier for the completion.

object'chat.completion' required

createdinteger required

Unix timestamp of creation.

modelstring required

Model used for the completion.

system_fingerprintstring

Fingerprint of the system configuration used.

generation_settingsobject

The generation settings used for the completion.

promptstring

The processed prompt.

truncatedboolean

True if the context size was exceeded.

tokens_cachedinteger

Number of tokens from the prompt which were reused from a cache.

tokens_evaluatedinteger

Number of tokens evaluated in total from the prompt.