レスポンスs API - ToAPIs Documentation

curl --request POST \
  --url https://toapis.com/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.3-codex-official",
    "instructions": "You are a professional code assistant",
    "input": "Write a quicksort in Python"
  }'

{
  "id": "<string>",
  "object": "<string>",
  "status": "<string>",
  "output": [
    {}
  ],
  "usage": {}
}

POST

responses

curl --request POST \
  --url https://toapis.com/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.3-codex-official",
    "instructions": "You are a professional code assistant",
    "input": "Write a quicksort in Python"
  }'

{
  "id": "<string>",
  "object": "<string>",
  "status": "<string>",
  "output": [
    {}
  ],
  "usage": {}
}

The レスポンスs API is OpenAI’s newer agentic API. Compared with Chat Completions, it adds richer tool use and server-side conversation state.

Function calling: let models call custom functions
Built-in tools: use tools such as web_search_preview
Server-side context: use previous_response_id instead of resending the full conversation
Reasoning control: tune thinking depth with reasoning.effort

モデル marked as レスポンスs Only, such as gpt-5-pro-official and gpt-5.3-codex-official, only support this API and do not support Chat Completions. See the model list for details.

Authorizations

Authorization

string

必須

Use Bearer Token authentication.

Authorization: Bearer YOUR_API_KEY

Get your API key from the API Key management page.

Body

model

string

必須

モデル name.Examples: "gpt-5-pro-official", "gpt-5.3-codex-official", "gpt-5.2-official"

input

string | object[]

必須

User input. Supports simple string input or a message array for multi-turn conversations.

instructions

string

System instructions that guide model behavior.

stream

boolean

デフォルト:false

Whether to enable streaming output.

max_output_tokens

integer

Maximum number of output tokens.

temperature

number

デフォルト:1

Sampling temperature, from 0 to 2.

top_p

number

デフォルト:1

Nucleus sampling threshold, from 0 to 1.

previous_response_id

string

Previous response ID for server-side multi-turn context.

reasoning

object

Reasoning configuration. reasoning.effort can be high, medium, low, or none.

tools

object[]

Available tools. Supported tool types include function and web_search_preview.

tool_choice

string

デフォルト:"auto"

Tool selection policy: auto, none, or required.