Openai Compatible Responses Api

Headers

x-api-key

string | null

Your API key.

Body

application/json

Request model for creating a response.

model

string

required

Model ID to use for the response.

Required string length: 1 - 255

input

required

The input to the model. Can be a simple string or an array of input items including reasoning from previous turns.

instructions

string | null

System instructions for the model.

Maximum string length: 32000

Example:

"You are a helpful AI assistant."

max_output_tokens

integer | null

Maximum number of tokens to generate.

Required range: x > 0

Example:

1024

temperature

number | null

default:1

Sampling temperature between 0 and 2.

Required range: 0 <= x <= 2

Example:

0.7

top_p

number | null

default:1

Nucleus sampling parameter.

Required range: 0 <= x <= 1

Example:

0.9

tools

ResponsesFunction · object[] | null

List of tools the model may call.

Show child attributes

tools.name

string

required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Maximum string length: 64

tools.parameters

FunctionParameters · object

required

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

Show child attributes

tools.parameters.type

string

default:object

Allowed value: "object"

tools.parameters.required

string[] | null

which one of the parameter is required

Example:

"location"

tools.parameters.properties

Properties · object

A map of property names to their types and descriptions. Each property is an object with 'type' and 'description' fields. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Example:

{
  "location": {
    "description": "The city and state, e.g. San Francisco, CA",
    "type": "string"
  },
  "unit": {
    "description": "Unit for the output - one of (celsius, fahrenheit)",
    "type": "string"
  }
}

tools.type

string

default:function

Allowed value: "function"

tools.description

string | null

A description of what the function does, used by the model to choose when and how to call the function.

Maximum string length: 1024

Example:

"Get the current weather in a given location"

tool_choice

default:auto

Controls which tool is called by the model.

Available options:

auto,

none,

required

parallel_tool_calls

boolean

default:true

Whether to enable parallel function calling.

stream

boolean | null

default:false

Whether to stream the response using server-sent events.

text

Text · object

Text output format configuration.

Text
JSONSchema

Show child attributes

text.type

string

default:text

The type of response format being defined. Always text.

Allowed value: "text"

reasoning

Reasoning · object

Configuration options for reasoning models.

Show child attributes

reasoning.effort

enum<string>

default:medium

Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Available options:

minimal,

low,

medium,

high

reasoning.summary

enum<string> | null

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.

Available options:

auto,

concise,

detailed

Example:

"auto"

Response

Successful Response

Response object from the Responses API.

string

required

Unique identifier for the response.

created_at

integer

required

Unix timestamp (in seconds) of when this Response was created.

model

string

required

Model ID used to generate the response, like moonshotai/kimi-k2 or anthropic/claude-sonnet-4-5. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model library to browse and compare available models.

status

enum<string>

required

The status of the response.

Available options:

in_progress,

completed,

failed,

cancelled,

incomplete

output

(ReasoningItem · object | OutputMessageItem · object | FunctionCallOutputItem · object)[]

required

An array of content items generated by the model. The length and order of items in the output array is dependent on the model's response. Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

Reasoning output item containing the model's thinking process.

ReasoningItem
OutputMessageItem
FunctionCallOutputItem

Show child attributes

output.id

string

required

Unique identifier for the reasoning item.

output.summary

ReasoningSummaryText · object[]

required

Reasoning summary content.

Show child attributes

output.summary.text

string

required

A summary of the reasoning output from the model so far.

output.summary.type

string

default:summary_text

Allowed value: "summary_text"

output.type

string

default:reasoning

Allowed value: "reasoning"

output.status

enum<string> | null

Status of the reasoning generation.

Available options:

in_progress,

completed,

incomplete

output.content

ReasoningContentText · object[] | null

Reasoning text content.

Show child attributes

output.content.text

string

required

The reasoning text from the model.

output.content.type

string

default:reasoning_text

Allowed value: "reasoning_text"

output.encrypted_content

string | null

The encrypted content of the reasoning item.

object

string

default:response

The object type of this resource - always set to 'response'.

Allowed value: "response"

conversation

ResponseConversation · object

The conversation that this response belongs to. Input items and output items from this response are automatically added to this conversation.

Show child attributes

conversation.id

string

required

The unique ID of the conversation.

usage

ResponseUsage · object

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.

Show child attributes

usage.input_tokens

integer

required

The number of input tokens.

usage.output_tokens

integer

required

The number of output tokens.

usage.total_tokens

integer

required

The total number of tokens used.

usage.input_tokens_details

Input Tokens Details · object

A detailed breakdown of the input tokens.

Show child attributes

usage.input_tokens_details.{key}

integer

Example:

{ "cached_tokens": 0 }

usage.output_tokens_details

Output Tokens Details · object

A detailed breakdown of the output tokens.

Show child attributes

usage.output_tokens_details.{key}

integer

Example:

{ "reasoning_tokens": 50 }

error

Error · object

An error object returned when the model fails to generate a Response.

Show child attributes

error.{key}

string

incomplete_details

Incomplete Details · object

Details if the response is incomplete.

instructions

string | null

The instructions provided for this response.

max_output_tokens

integer | null

Maximum output tokens configured.

parallel_tool_calls

boolean

default:true

Whether parallel tool calls are enabled.

reasoning

Reasoning · object

Configuration options for reasoning models.

Show child attributes

reasoning.effort

enum<string>

default:medium

Available options:

minimal,

low,

medium,

high

reasoning.summary

enum<string> | null

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of auto, concise, or detailed.

Available options:

auto,

concise,

detailed

Example:

"auto"

temperature

number

default:1

The temperature used for generation.

text

Text · object

Text format configuration.

Text
JSONSchema

Show child attributes

text.type

string

default:text

The type of response format being defined. Always text.

Allowed value: "text"

tool_choice

default:auto

The tool choice configuration.

Available options:

auto,

none,

required

tools

ResponsesFunction · object[]

The tools available to the model.

Show child attributes

tools.name

string

required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Maximum string length: 64

tools.parameters

FunctionParameters · object

required

Show child attributes

tools.parameters.type

string

default:object

Allowed value: "object"

tools.parameters.required

string[] | null

which one of the parameter is required

Example:

"location"

tools.parameters.properties

Properties · object

Example:

{
  "location": {
    "description": "The city and state, e.g. San Francisco, CA",
    "type": "string"
  },
  "unit": {
    "description": "Unit for the output - one of (celsius, fahrenheit)",
    "type": "string"
  }
}

tools.type

string

default:function

Allowed value: "function"

tools.description

string | null

A description of what the function does, used by the model to choose when and how to call the function.

Maximum string length: 1024

Example:

"Get the current weather in a given location"

top_p

number

default:1

The top_p value used for generation.

API reference

Headers

Body

Response