Skillintermediate

OpenAI - Response API

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

Claude Code Knowledge Pack7/10/2026

Overview

OpenAI - Response API

Usage

LiteLLM Python SDK

Non-streaming


# Non-streaming response
response = litellm.responses(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=100
)

print(response)

Streaming


# Streaming response
response = litellm.responses(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True
)

for event in response:
    print(event)

Web Search


response = litellm.responses(
    model="openai/gpt-5",
    input="What is the capital of France?",
    tools=[{
        "type": "web_search_preview",
        "search_context_size": "medium"  # Options: "low", "medium", "high"
    }]
)

print(response)

For full details, see the Web Search guide.

Image Generation with Streaming


# Streaming image generation with partial images
stream = litellm.responses(
    model="gpt-4.1",  # Use an actual image generation model
    input="Generate a gorgeous image of a river made of white owl feathers",
    stream=True,
    tools=[{"type": "image_generation", "partial_images": 2}],

)

for event in stream:
    if event.type == "response.image_generation_call.partial_image":
        idx = event.partial_image_index
        image_base64 = event.partial_image_b64
        image_bytes = base64.b64decode(image_base64)
        with open(f"river{idx}.png", "wb") as f:
            f.write(image_bytes)

GET a Response


# First, create a response
response = litellm.responses(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=100
)

# Get the response ID
response_id = response.id

# Retrieve the response by ID
retrieved_response = litellm.get_responses(
    response_id=response_id
)

print(retrieved_response)

# For async usage
# retrieved_response = await litellm.aget_responses(response_id=response_id)

DELETE a Response


# First, create a response
response = litellm.responses(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=100
)

# Get the response ID
response_id = response.id

# Delete the response by ID
delete_response = litellm.delete_responses(
    response_id=response_id
)

print(delete_response)

# For async usage
# delete_response = await litellm.adelete_responses(response_id=response_id)

LiteLLM Proxy with OpenAI SDK

Set up config.yaml

model_list:
  - model_name: openai/o1-pro
    litellm_params:
      model: openai/o1-pro
      api_key: os.environ/OPENAI_API_KEY

Start LiteLLM Proxy Server

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

Use OpenAI SDK with LiteLLM Proxy

Non-streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Non-streaming response
response = client.responses.create(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn."
)

print(response)

Streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Streaming response
response = client.responses.create(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True
)

for event in response:
    print(event)

Image Generation with Streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(api_key="sk-1234", base_url="http://localhost:4000")

stream = client.responses.create(
    model="gpt-4.1",
    input="Draw a gorgeous image of a river made of white owl feathers, snaking its way through a serene winter landscape",
    stream=True,
    tools=[{"type": "image_generation", "partial_images": 2}],
)

for event in stream:
    print(f"event: {event}")
    if event.type == "response.image_generation_call.partial_image":
        idx = event.partial_image_index
        image_base64 = event.partial_image_b64
        image_bytes = base64.b64decode(image_base64)
        with open(f"river{idx}.png", "wb") as f:
            f.write(image_bytes)

GET a Response

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# First, create a response
response = client.responses.create(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn."
)

# Get the response ID
response_id = response.id

# Retrieve the response by ID
retrieved_response = client.responses.retrieve(response_id)

print(retrieved_response)

DELETE a Response

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# First, create a response
response = client.responses.create(
    model="openai/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn."
)

# Get the response ID
response_id = response.id

# Delete the response by ID
delete_response = client.responses.delete(response_id)

print(delete_response)

Supported Responses API Parameters

Provider	Supported Parameters
`openai`	All Responses API parameters are supported

Reusable Prompts

Use the prompt parameter to reference a stored prompt template and optionally supply variables.


response = litellm.responses(
    model="openai/o1-pro",
    prompt={
        "id": "pmpt_abc123",
        "version": "2",
        "variables": {
            "customer_name": "Jane Doe",
            "product": "40oz juice box",
        },
    },
)

print(response)

The same parameter is supported when calling the LiteLLM proxy with the OpenAI SDK:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:4000", api_key="your-api-key")

response = client.responses.create(
    model="openai/o1-pro",
    prompt={
        "id": "pmpt_abc123",
        "version": "2",
        "variables": {
            "customer_name": "Jane Doe",
            "product": "40oz juice box",
        },
    },
)

print(response)

Computer Use


# Non-streaming response
response = litellm.responses(
    model="computer-use-preview",
    tools=[{
        "type": "computer_use_preview",
        "display_width": 1024,
        "display_height": 768,
        "environment": "browser" # other possible values: "mac", "windows", "ubuntu"
    }],    
    input=[
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Check the latest OpenAI news on bing.com."
            }
            # Optional: include a screenshot of the initial state of the environment
            # {
            #     type: "input_image",
            #     image_url: f"data:image/png;base64,{screenshot_base64}"
            # }
          ]
        }
    ],
    reasoning={
        "summary": "concise",
    },
    truncation="auto"
)

print(response.output)

Set up config.yaml

model_list:
  - model_name: openai/o1-pro
    litellm_params:
      model: openai/o1-pro
      api_key: os.environ/OPENAI_API_KEY

Start LiteLLM Proxy Server

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

Test it!

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Non-streaming response
response = client.responses.create(
    model="computer-use-preview",
    tools=[{
        "type": "computer_use_preview",
        "display_width": 1024,
        "display_height": 768,
        "environment": "browser" # other possible values: "mac", "windows", "ubuntu"
    }],    
    input=[
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Check the latest OpenAI news on bing.com."
            }
            # Optional: include a screenshot of the initial state of the environment
            # {
            #     type: "input_image",
            #     image_url: f"data:image/png;base64,{screenshot_base64}"
            # }
          ]
        }
    ],
    reasoning={
        "summary": "concise",
    },
    truncation="auto"
)

print(response)

MCP Tools


from typing import Optional

# Configure MCP Tools
MCP_TOOLS = [
    {
        "type": "mcp",
        "server_label": "deepwiki",
        "server_url": "https://mcp.deepwiki.com/mcp",
        "allowed_tools": ["ask_question"]
    }
]

# Step 1: Make initial request - OpenAI will use MCP LIST and return MCP calls for approval
response = litellm.responses(
    model="openai/gpt-4.1",
    tools=MCP_TOOLS,
    input="What transport protocols does the 2025-03-26 version of the MCP spec support?"
)

# Get the MCP approval ID
mcp_approval_id = None
for output in response.output:
    if output.type == "mcp_approval_request":
        mcp_approval_id = output.id
        break

# Step 2: Send followup with approval for the MCP call
response_with_mcp_call = litellm.responses(
    model="openai/gpt-4.1",
    tools=MCP_TOOLS,
    input=[
        {
            "type": "mcp_approval_response",
            "approve": True,
            "approval_request_id": mcp_approval_id
        }
    ],
    previous_response_id=response.id,
)

print(response_with_mcp_call)

Set up config.yaml

model_list:
  - model_name: openai/gpt-4.1
    litellm_params:
      model: openai/gpt-4.1
      api_key: os.environ/OPENAI_API_KEY

Start LiteLLM Proxy Server

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

Test it!

from openai import OpenAI
from typing import Optional

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Configure MCP Tools
MCP_TOOLS = [
    {
        "type": "mcp",
        "server_label": "deepwiki",
        "server_url": "https://mcp.deepwiki.com/mcp",
        "allowed_tools": ["ask_question"]
    }
]

# Step 1: Make initial request - OpenAI will use MCP LIST and return MCP calls for approval
response = client.responses.create(
    model="openai/gpt-4.1",
    tools=MCP_TOOLS,
    input="What transport protocols does the 2025-03-26 version of the MCP spec support?"
)

# Get the MCP approval ID
mcp_approval_id = None
for output in response.output:
    if output.type == "mcp_approval_request":
        mcp_approval_id = output.id
        break

# Step 2: Send followup with approval for the MCP call
response_with_mcp_call = client.responses.create(
    model="openai/gpt-4.1",
    tools=MCP_TOOLS,
    input=[
        {
            "type": "mcp_approval_response",
            "approve": True,
            "approval_request_id": mcp_approval_id
        }
    ],
    previous_response_id=response.id,
)

print(response_with_mcp_call)

Verbosity Parameter

The verbosity parameter is supported for the responses API.

from litellm import responses

question = "Write a poem about a boy and his first pet dog."

for verbosity in ["low", "medium", "high"]:
    response = responses(
        model="gpt-5-mini",
        input=question,
        text={"verbosity": verbosity}
    )

    print(response)

from openai import OpenAI

from IPython.display import display

client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

question = "Write a poem about a boy and his first pet dog."

data = []

for verbosity in ["low", "medium", "high"]:
    response = client.responses.create(
        model="gpt-5-mini",
        input=question,
        text={"verbosity": verbosity}
    )

    # Extract text
    output_text = ""
    for item in response.output:
        if hasattr(item, "content"):
            for content in item.content:
                if hasattr(content, "text"):
                    output_text += content.text

    usage = response.usage
    data.append({
        "Verbosity": verbosity,
        "Sample Output": output_text,
        "Output Tokens": usage.output_tokens
    })

# Create DataFrame
df = pd.DataFrame(data)

# Display nicely with centered headers
pd.set_option('display.max_colwidth', None)
styled_df =