Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Headers
Optional metadata for the request
Body
Parameters for generating model responses.
Model identifier to generate the response
Text, image, or file inputs to the model
Whether to run the model response in the background
Additional output data to include
System message as first item in context
Upper bound for tokens generated
Key-value pairs for additional information
Allow parallel tool calls
ID of previous response for multi-turn
Configuration for reasoning models
Latency tier for processing
auto
, default
, flex
Whether to store the response
Enable streaming response
Sampling temperature between 0 and 2
Text response configuration
Tool selection behavior
none
Available tools for the model
Nucleus sampling parameter
Truncation strategy
auto
, disabled
End-user identifier
Response
Model Response generated successfully.
Response ID.
Object type.
Creation timestamp.
Response status.
Maximum output tokens allowed.
Model used for the response.
Indicates if parallel tool calls were used.
ID of the previous response, if any.
Reasoning details.
Service tier.
Indicates if the response is stored.
Temperature setting for the model.
Tool choice used.
Tools used in the response.
Top-p sampling parameter.
Truncation setting.
Additional metadata.
Provider of the response.
Error details, if any.
Details about incomplete responses, if any.
Instructions provided for the response.
User details, if any.