Implementation:Openai Openai python Completion Model

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

Overview

Concrete type for the legacy Completion response object provided by the openai-python SDK.

Description

The Completion Pydantic model represents a response from the legacy completions API endpoint (/v1/completions). It contains an id, a list of choices (each a CompletionChoice), a created timestamp, the model used, an object type fixed to "text_completion", an optional system_fingerprint for tracking backend configuration, and optional usage statistics. Note that both streamed and non-streamed responses share the same shape, unlike the chat endpoint.

Usage

Import this type when working with the legacy completions endpoint via client.completions.create(). For modern chat-based completions, use the chat completion types instead.

Code Reference

Source Location

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

Signature

class Completion(BaseModel):
    id: str
    choices: List[CompletionChoice]
    created: int
    model: str
    object: Literal["text_completion"]
    system_fingerprint: Optional[str] = None
    usage: Optional[CompletionUsage] = None

Import

from openai.types import Completion

I/O Contract

Fields

Name	Type	Required	Description
id	str	Yes	Unique identifier for the completion
choices	List[CompletionChoice]	Yes	List of completion choices generated for the input prompt
created	int	Yes	Unix timestamp (seconds) when the completion was created
model	str	Yes	The model used for completion
object	Literal["text_completion"]	Yes	Object type, always "text_completion"
system_fingerprint	Optional[str]	No	Backend configuration fingerprint for determinism tracking
usage	Optional[CompletionUsage]	No	Token usage statistics for the request

Usage Examples

from openai import OpenAI

client = OpenAI()

completion = client.completions.create(
    model="gpt-3.5-turbo-instruct",
    prompt="Say hello in French:",
    max_tokens=50,
)
print(completion.id)
print(completion.choices[0].text)
if completion.usage:
    print(f"Tokens used: {completion.usage.total_tokens}")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus