ToAPIsToAPIs
Responses Format

Responses API

OpenAI Responses API format with function calling, built-in tools, and server-side multi-turn context

POST
/v1/responses

Note for users in mainland China: Please use https://toapis.cn as the API endpoint (Base URL). Replace https://toapis.com with https://toapis.cn in the examples in this document.

The Responses 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

Models marked as Responses 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

Authorizationstringheaderrequired

Use Bearer Token authentication.

Authorization: Bearer YOUR_API_KEY

Get your API key from the API Key management page.

Body

modelstringbodyrequired

Model name.

Examples: "gpt-5-pro-official", "gpt-5.3-codex-official", "gpt-5.2-official"

inputstring | object[]bodyrequired

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

instructionsstringbody

System instructions that guide model behavior.

streambooleanbodydefault: false

Whether to enable streaming output.

max_output_tokensintegerbody

Maximum number of output tokens.

temperaturenumberbodydefault: 1

Sampling temperature, from 0 to 2.

top_pnumberbodydefault: 1

Nucleus sampling threshold, from 0 to 1.

previous_response_idstringbody

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

reasoningobjectbody

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

toolsobject[]body

Available tools. Supported tool types include function and web_search_preview.

tool_choicestringbodydefault: auto

Tool selection policy: auto, none, or required.

Response

idstring

Unique response ID, usable as previous_response_id.

objectstring

Always response.

statusstring

Response status: completed, failed, or in_progress.

outputobject[]

Output items, such as message, function_call, reasoning, or web_search_call.

usageobject

Token usage statistics, including input, output, reasoning, and total tokens.

requestExample

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"
  }'
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://toapis.com/v1"
)

response = client.responses.create(
    model="gpt-5.3-codex-official",
    instructions="You are a professional code assistant",
    input="Write a quicksort in Python"
)

print(response.output[0].content[0].text)