gpt-5-mini not found

[Jarvx]

Initial Checks

• I confirm that I'm using Pydantic V2
• confrim that I'm using pydantic_ai 1.0.0b1

Description

I am using OpenAI models and got this error. I am very confused that gpt-5-mini is out there.

 status_code: 404, model_name: gpt-5-mini, body: {'detail': 'Not Found'}

Here is the stacktrace:

  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/agent/abstract.py", line 316, in run_sync
    return get_event_loop().run_until_complete(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/agent/abstract.py", line 217, in run
    async for node in agent_run:
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/run.py", line 150, in __anext__
    next_node = await self._graph_run.__anext__()
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_graph/graph.py", line 761, in __anext__
    return await self.next(self._next_node)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_graph/graph.py", line 734, in next
    self._next_node = await node.run(ctx)
                      ^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/_agent_graph.py", line 378, in run
    return await self._make_request(ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/_agent_graph.py", line 420, in _make_request
    model_response = await ctx.deps.model.request(message_history, model_settings, model_request_parameters)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/models/openai.py", line 337, in request
    response = await self._completions_create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/pydantic_ai/models/openai.py", line 445, in _completions_create
    raise ModelHTTPError(status_code=status_code, model_name=self.model_name, body=e.body) from e
pydantic_ai.exceptions.ModelHTTPError: status_code: 404, model_name: gpt-5-mini, body: {'detail': 'Not Found'}

Example Code

Python, Pydantic & OS Version

pydantic version: 2.11.5
        pydantic-core version: 2.33.2
          pydantic-core build: profile=release pgo=false
               python version: 3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]
                     platform: Linux-6.8.0-48-generic-x86_64-with-glibc2.35
             related packages: pydantic-settings-2.9.1 typing_extensions-4.13.2 pyright-1.1.368 typing_extensions-4.11.0 mypy-0.942
                       commit: unknown

[DouweM]

@Jarvx Can you please share the code you're running? Specifically I want to know if you're using the official OpenAI API, or some other OpenAI-compatible API.

[Jarvx]

@Jarvx Can you please share the code you're running? Specifically I want to know if you're using the official OpenAI API, or some other OpenAI-compatible API.

Thanks for the prompt reply. I need some time to extract the code. But I can tell, I am using offical OpenAI API.

[DouweM]

@Jarvx Does it work with the OpenAIResponsesModel? Does it work when using OpenAI's SDK directly? Either way this very much looks like an OpenAI API issue not really something we can fix on the Pydantic AI side.

[Jarvx]

It's a chatmodel

Python 3.12.7 (main, Oct 16 2024, 04:37:19) [Clang 18.1.8 ] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from pydantic_ai.models import Model, infer_model
>>> model = infer_model("openai:gpt-5-mini")
>>> type(model)
<class 'pydantic_ai.models.openai.OpenAIChatModel'>

[DouweM]

@Jarvx It's working for me. https://platform.openai.com/docs/models/gpt-5-mini suggests it's not available on the Free tier. I think that's likely your issue.