Implementation:Openai Openai python Shared Responses Model
Appearance
| Knowledge Sources | |
|---|---|
| Domains | API_Types, Python |
| Last Updated | 2026-02-15 00:00 GMT |
Overview
Concrete tool for defining the union type of model identifiers accepted by the Responses API provided by the openai-python SDK.
Description
ResponsesModel is a TypeAlias representing a union of all model identifiers accepted by the OpenAI Responses API. It combines:
- str - Any arbitrary model string for forward compatibility.
- ChatModel - The full set of chat model literal identifiers.
- A Literal union of additional model identifiers specific to the Responses API, including o1-pro, o3-pro, o3-deep-research, o4-mini-deep-research, computer-use-preview, gpt-5-codex, gpt-5-pro, and gpt-5.1-codex-max variants.
This type alias is structurally identical to AllModels but is semantically scoped to the Responses API surface.
Usage
Import ResponsesModel when you need to type-annotate model parameters specifically for the Responses API.
Code Reference
Source Location
- Repository: openai-python
- File: src/openai/types/shared/responses_model.py
Signature
ResponsesModel: TypeAlias = Union[
str,
ChatModel,
Literal[
"o1-pro",
"o1-pro-2025-03-19",
"o3-pro",
"o3-pro-2025-06-10",
"o3-deep-research",
"o3-deep-research-2025-06-26",
"o4-mini-deep-research",
"o4-mini-deep-research-2025-06-26",
"computer-use-preview",
"computer-use-preview-2025-03-11",
"gpt-5-codex",
"gpt-5-pro",
"gpt-5-pro-2025-10-06",
"gpt-5.1-codex-max",
],
]
Import
from openai.types.shared import ResponsesModel
I/O Contract
Type Members
| Variant | Description |
|---|---|
| str | Any arbitrary model identifier string for forward compatibility. |
| ChatModel | All chat model literals (gpt-4o, gpt-4, gpt-3.5-turbo, o1, o3, etc.). |
| Literal["o1-pro", ...] | Additional model identifiers for the Responses API: o1-pro, o3-pro, o3-deep-research, o4-mini-deep-research, computer-use-preview, gpt-5-codex, gpt-5-pro, gpt-5.1-codex-max, and their dated variants. |
Usage Examples
from openai import OpenAI
from openai.types.shared import ResponsesModel
def create_response(model: ResponsesModel, prompt: str):
"""Create a response using any valid Responses API model."""
client = OpenAI()
response = client.responses.create(
model=model,
input=prompt,
)
return response
# All of these are valid ResponsesModel values
result = create_response("gpt-4o", "Hello!")
result = create_response("o3-pro", "Solve this problem...")
result = create_response("computer-use-preview", "Navigate to...")
Related Pages
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment