Implementation:Openai Openai python Response Text Done Event

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Responses_API
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete type for representing an event emitted when text content output is finalized during streaming, provided by the openai-python SDK.

Description

ResponseTextDoneEvent is a Pydantic model representing the response.output_text.done streaming event. It is emitted when the model has finished generating a text output content part. The event carries the complete text, a logprobs list of Logprob objects (each containing token, logprob, and optional top_logprobs), and positional fields content_index, item_id, output_index, and sequence_number. The module also defines supporting classes Logprob and LogprobTopLogprob.

Usage

Import this type when you need to capture the finalized text output along with its log probabilities from a streaming response.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/response_text_done_event.py

Signature

class ResponseTextDoneEvent(BaseModel):
    """Emitted when text content is finalized."""

    content_index: int
    item_id: str
    logprobs: List[Logprob]
    output_index: int
    sequence_number: int
    text: str
    type: Literal["response.output_text.done"]

Import

from openai.types.responses import ResponseTextDoneEvent

I/O Contract

Fields

Name	Type	Required	Description
content_index	int	Yes	The index of the content part that the text content is finalized.
item_id	str	Yes	The ID of the output item that the text content is finalized.
logprobs	List[Logprob]	Yes	The log probabilities of the tokens. Each Logprob has token (str), logprob (float), and optional top_logprobs (List[LogprobTopLogprob]).
output_index	int	Yes	The index of the output item that the text content is finalized.
sequence_number	int	Yes	The sequence number for this event.
text	str	Yes	The text content that is finalized.
type	Literal["response.output_text.done"]	Yes	The type of the event. Always response.output_text.done.

Usage Examples

import openai

client = openai.OpenAI()

stream = client.responses.create(
    model="gpt-4o",
    input="What is the capital of France?",
    stream=True,
)

for event in stream:
    if event.type == "response.output_text.done":
        print(f"Final text: {event.text}")
        if event.logprobs:
            for lp in event.logprobs[:5]:
                print(f"  Token: {lp.token!r}, logprob: {lp.logprob:.4f}")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus