ResponsesRequest schema

Field Type and description

model
Required

string

Model id of any text model in the catalog (e.g., openai/gpt-5.6-luna, deepseek-ai/DeepSeek-V4-Pro).

input

schema

The input prompt or items for the model. When the last message in the conversation is from the assistant, the model answers with a new assistant message.

oneOf

string

array of object

Array items

object

instructions

string

System or developer instructions directing the model's behavior.

max_output_tokens

integer

Maximum number of output tokens to generate: a whole number from 1 to the model's own max_output_tokens in GET /v1/models. A larger value, or one that is not a whole number, returns HTTP 400 invalid_max_tokens. When omitted, the reply is limited to the model's default output length, which is at most its max_output_tokens.

minimum: 1

reasoning

object

Reasoning configuration object.

Field Type and description

effort

string

Desired effort level for model reasoning.

Allowed values: ["none","low","medium","high","xhigh"]

temperature

number

Sampling temperature.

top_p

number

Nucleus sampling probability.

presence_penalty

number

Presence penalty parameter.

frequency_penalty

number

Frequency penalty parameter.

user

string

A unique identifier representing your end-user.

text

schema

Text configuration or content.

oneOf

string

object

metadata

object

Developer-assigned metadata for the response.

tools

array of object

Tools the model may call. Supported tool types: function and namespace (a named group of function tools). A call to a function declared in a namespace tool is returned with a separate namespace field.

Array items

object

Field	Type and description
`type` Required	string `function` or `namespace`.

tool_choice

schema

auto, none, required, or { "type": "function", "name": "..." } to require one function.

oneOf

string

Allowed values: ["auto","none","required"]

object

Field	Type and description
`type` Required	string Allowed values: `["function"]`
`name` Required	string

parallel_tool_calls

boolean

Whether the model may call several tools in one turn.

service_tier

string

Service tier.

truncation

schema

Truncation strategy for the conversation.

oneOf

string

object

store

boolean

store is always treated as false.

default: false

stream

boolean

Set to true to receive the response as Server-Sent Events.

default: false