Responses API

The Responses API is OpenAI's next-generation interface for interacting with language models. It supports multi-turn conversations via previous_response_id, stateful interactions, and built-in tool calling.

Endpoint Info

Item	Value
URL	/v1/responses
Method	POST
Auth	Bearer Token (API Key)
Content-Type	application/json

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Model ID, e.g. gpt-4o-mini
input	string / array	Yes	Input text or message array
instructions	string	No	System-level instructions for the model
previous_response_id	string	No	ID of a previous response for multi-turn context
max_output_tokens	integer	No	Maximum number of output tokens
temperature	number	No	Sampling temperature, 0–2. Default 1
top_p	number	No	Nucleus sampling, 0–1
stream	boolean	No	Enable streaming output. Default false
tools	array	No	Tool definitions for function calling
tool_choice	string/object	No	Tool selection mode: auto, none, or specific tool

cURL Examples

Normal Request

curl https://api.quickapi.store/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "What is the capital of France?",
    "max_output_tokens": 1000
  }'

Streaming Request

curl https://api.quickapi.store/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Tell me a short story",
    "stream": true
  }'

With Instructions

curl https://api.quickapi.store/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "input": "Explain quantum computing",
    "instructions": "You are a physics professor. Explain concepts clearly.",
    "max_output_tokens": 2000
  }'

Multi-turn with previous_response_id

curl https://api.quickapi.store/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "And what is its population?",
    "previous_response_id": "resp_abc123def456"
  }'

💡 Multi-turn Conversations

Use previous_response_id to chain responses. The model retains the full conversation context from prior turns, enabling natural multi-turn dialogue without resending the entire history.

Response Example

Normal Response

{
  "id": "resp_abc123def456",
  "object": "response",
  "created_at": 1700000000,
  "model": "gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The capital of France is Paris."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 8,
    "total_tokens": 20
  }
}

Streaming Response

data: {"type":"response.output_text.delta","delta":"The"}

data: {"type":"response.output_text.delta","delta":" capital"}

data: {"type":"response.output_text.delta","delta":" of"}

data: {"type":"response.output_text.delta","delta":" France"}

data: {"type":"response.output_text.delta","delta":" is"}

data: {"type":"response.output_text.delta","delta":" Paris."}

data: {"type":"response.completed","response":{"id":"resp_abc123def456","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"The capital of France is Paris."}]}]}}

data: [DONE]

Python Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.quickapi.store/v1",
    api_key="YOUR_API_KEY"
)

# Normal request
response = client.responses.create(
    model="gpt-4o-mini",
    input="What is the capital of France?"
)
print(response.output[0].content[0].text)

# Streaming request
for event in client.responses.create(
    model="gpt-4o-mini",
    input="Tell me a short story",
    stream=True
):
    if hasattr(event, 'delta'):
        print(event.delta, end="")

# Multi-turn conversation
first = client.responses.create(
    model="gpt-4o-mini",
    input="What is the capital of France?"
)
second = client.responses.create(
    model="gpt-4o-mini",
    input="And what is its population?",
    previous_response_id=first.id
)
print(second.output[0].content[0].text)

⚠️ API Compatibility

The Responses API is OpenAI's newest interface. Ensure your SDK version supports client.responses.create(). Older SDK versions may not include this endpoint.