Create a response

View as Markdown
Responses API endpoint for dynamically resolved models. This is used for models that support the Responses API structure.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.
inputstring or list of objectsRequired
Input for the response.
modelstring or nullOptionalDefaults to qwen/qwen3-max
Model identifier.
templatestring or nullOptional
Template name or UUID to expand before inference.
variablesmap from strings to strings or nullOptional

Values used when rendering {{slot}} placeholders.

session_idstring or nullOptional

Caller-defined grouping key for usage reporting.

streambooleanOptionalDefaults to false
When true, returns SSE chunks instead of a JSON object.
max_output_tokensinteger or nullOptional>=1
Maximum number of output tokens to generate.
temperaturedouble or nullOptional
Sampling temperature.
top_pdouble or nullOptional
Nucleus sampling threshold.
seedinteger or nullOptional

Optional seed for best-effort determinism.

reasoningobject or nullOptional
Optional reasoning parameters.
toolslist of objects or nullOptional
Tool definitions.
tool_choiceenum or object or nullOptional
Controls tool calling.
response_formatobject or nullOptional

Optional response format constraints (e.g. JSON schema).

pluginslist of objects or nullOptional
Optional plugins to use.
userstring or nullOptional<=256 characters

End-user identifier for abuse monitoring.

Response

Successful response.

Errors

401
Unauthorized Error
422
Unprocessable Entity Error