Implementation:Openai Openai python Response Model

Knowledge Sources	openai-python OpenAI Response Object
Domains	NLP, Text_Generation
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete typed response model and streaming manager for extracting Responses API outputs provided by the OpenAI Python SDK.

Description

The Response Pydantic model represents a complete Responses API result with output items, status, usage, and metadata. The ResponseStreamManager context manager provides high-level streaming with .text_stream for text deltas and event iteration for fine-grained control over 30+ event types.

Usage

Access .output_text for simple text extraction. Iterate .output for all output items. Use ResponseStreamManager as a context manager for streaming responses.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/response.py
• Lines: L1-320
• File: src/openai/lib/streaming/responses.py (ResponseStreamManager)

Signature

class Response(BaseModel):
    id: str
    created_at: float
    model: str
    object: Literal["response"]
    output: List[ResponseOutputItem]
    output_text: str  # Convenience property for first text output
    status: Literal["completed", "failed", "in_progress", "incomplete"]
    usage: ResponseUsage
    error: Optional[ResponseError] = None
    incomplete_details: Optional[IncompleteDetails] = None
    instructions: Optional[str] = None
    metadata: Optional[Dict[str, str]] = None
    previous_response_id: Optional[str] = None
    temperature: Optional[float] = None
    top_p: Optional[float] = None
    tool_choice: Optional[str] = None
    tools: Optional[List[Tool]] = None

class ResponseStreamManager(Generic[TextFormatT]):
    """High-level streaming context manager."""
    @property
    def text_stream(self) -> Iterator[str]: ...

    def __enter__(self) -> ResponseStream[TextFormatT]: ...
    def __exit__(self, ...) -> None: ...

    def get_final_response(self) -> Response: ...
    def get_final_text(self) -> str: ...

Import

from openai.types.responses import Response
# ResponseStreamManager returned by client.responses.stream()

I/O Contract

Inputs

Name	Type	Required	Description
response	Response or ResponseStreamManager	Yes	Raw API response from create()/stream()

Outputs

Name	Type	Description
output_text	str	First text output (convenience accessor)
output	list[ResponseOutputItem]	All output items (text, tool calls, etc.)
status	str	Response status (completed/failed/in_progress/incomplete)
usage	ResponseUsage	Token usage (input_tokens, output_tokens, total_tokens)
id	str	Response ID for retrieval/chaining

Usage Examples

Extract Text

from openai import OpenAI

client = OpenAI()
response = client.responses.create(
    model="gpt-4o",
    input="What is machine learning?",
)
print(response.output_text)
print(f"Tokens: {response.usage.total_tokens}")

Iterate Output Items

response = client.responses.create(
    model="gpt-4o",
    input="Analyze this data.",
    tools=[{"type": "web_search"}],
)

for item in response.output:
    if item.type == "message":
        for content in item.content:
            if content.type == "output_text":
                print(content.text)
    elif item.type == "web_search_call":
        print(f"Searched: {item.id}")

Streaming with Text Stream

with client.responses.stream(
    model="gpt-4o",
    input="Tell me a story.",
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

    final = stream.get_final_response()
    print(f"\nTotal tokens: {final.usage.total_tokens}")

Related Pages

Implements Principle

• Principle:Openai_Openai_python_Response_Processing

Requires Environment

• Environment:Openai_Openai_python_Python_3_9_Plus