`OpenAIChatModel` `model_name` typing is too restrictive for non-OpenAI providers

[kkestell]

Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue in https://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

When using OpenAIChatModel with a non-OpenAI provider such as OllamaProvider, passing a custom model name fails static type checking. At runtime this works fine. The problem is the type signature for model_name, which is tied to a massive Literal[...] of OpenAI model names. This breaks legitimate use cases where providers expose other model identifiers.

Reproduction

from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.ollama import OllamaProvider

model = OpenAIChatModel(
    model_name="gpt-oss:20b",
    provider=OllamaProvider(base_url="http://localhost:11434/v1"),
)

Actual error

Unexpected type(s):
(Literal["gpt-oss:20b"], OllamaProvider)
Possible type(s):
(Literal["gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-5-2025-08-07", "gpt-5-mini-2025-08-07", "gpt-5-nano-2025-08-07", "gpt-5-chat-latest", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-4.1-2025-04-14", "gpt-4.1-mini-2025-04-14", "gpt-4.1-nano-2025-04-14", "o4-mini", "o4-mini-2025-04-16", "o3", "o3-2025-04-16", "o3-mini", "o3-mini-2025-01-31", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12", "o1-mini", "o1-mini-2024-09-12", "gpt-4o", "gpt-4o-2024-11-20", "gpt-4o-2024-08-06", "gpt-4o-2024-05-13", "gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01", "gpt-4o-audio-preview-2024-12-17", "gpt-4o-audio-preview-2025-06-03", "gpt-4o-mini-audio-preview", "gpt-4o-mini-audio-preview-2024-12-17", "gpt-4o-search-preview", "gpt-4o-mini-search-preview", "gpt-4o-search-preview-2025-03-11", "gpt-4o-mini-search-preview-2025-03-11", "chatgpt-4o-latest", "codex-mini-latest", "gpt-4o-mini", "gpt-4o-mini-2024-07-18", "gpt-4-turbo", "gpt-4-turbo-2024-04-09", "gpt-4-0125-preview", "gpt-4-turbo-preview", "gpt-4-1106-preview", "gpt-4-vision-preview", "gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613", "gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125", "gpt-3.5-turbo-16k-0613", "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"] | str, Literal['azure', 'deepseek', 'cerebras', 'fireworks', 'github', 'grok', 'heroku', 'moonshotai', 'ollama', 'openai', 'openai-chat', 'openrouter', 'together', 'vercel', 'litellm'])
(Literal["gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-5-2025-08-07", "gpt-5-mini-2025-08-07", "gpt-5-nano-2025-08-07", "gpt-5-chat-latest", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-4.1-2025-04-14", "gpt-4.1-mini-2025-04-14", "gpt-4.1-nano-2025-04-14", "o4-mini", "o4-mini-2025-04-16", "o3", "o3-2025-04-16", "o3-mini", "o3-mini-2025-01-31", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12", "o1-mini", "o1-mini-2024-09-12", "gpt-4o", "gpt-4o-2024-11-20", "gpt-4o-2024-08-06", "gpt-4o-2024-05-13", "gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01", "gpt-4o-audio-preview-2024-12-17", "gpt-4o-audio-preview-2025-06-03", "gpt-4o-mini-audio-preview", "gpt-4o-mini-audio-preview-2024-12-17", "gpt-4o-search-preview", "gpt-4o-mini-search-preview", "gpt-4o-search-preview-2025-03-11", "gpt-4o-mini-search-preview-2025-03-11", "chatgpt-4o-latest", "codex-mini-latest", "gpt-4o-mini", "gpt-4o-mini-2024-07-18", "gpt-4-turbo", "gpt-4-turbo-2024-04-09", "gpt-4-0125-preview", "gpt-4-turbo-preview", "gpt-4-1106-preview", "gpt-4-vision-preview", "gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613", "gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125", "gpt-3.5-turbo-16k-0613", "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"] | str, Literal['azure', 'deepseek', 'cerebras', 'fireworks', 'github', 'grok', 'heroku', 'moonshotai', 'ollama', 'openai', 'openai-chat', 'openrouter', 'together', 'vercel', 'litellm'])

Expected
Any str should be valid for model_name when using providers other than OpenAI.

Notes
The current typing assumes all providers share OpenAI’s catalog of models, which is not true. For Ollama and others, model_name: str should be sufficient.

Example Code

from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.ollama import OllamaProvider

model = OpenAIChatModel(
    model_name="gpt-oss:20b",
    provider=OllamaProvider(base_url="http://localhost:11434/v1"),
)

Python, Pydantic AI & LLM client version

* Python 3.13
* pydantic-ai 1.0.10
* Ollama 0.12.0 w/ gpt-oss:20b

[ixenion]

Using neo vim with pyright and dont see any typing errors:

[DouweM]

We already allow str:

pydantic-ai/pydantic_ai_slim/pydantic_ai/models/openai.py

Line 98 in 79ef2bf

OpenAIModelName = str | AllModels

And we use this in the test suite without typing issues. What type checker are you using?