What happened?

Describe the bug
Currently, Autogen does not support GPT-5 when initializing agents or making API calls. Attempts to set the model parameter to "gpt-5" or "gpt-5-nano" result in an InvalidRequestError from the OpenAI API, indicating that the model is unrecognized or unsupported in the current Autogen release.

Additional context

• OpenAI has released GPT-5, but Autogen currently do not supports in its default configuration.
• This limits users who want to leverage GPT-5's features in multi-agent orchestration.
• Requesting the addition of GPT-5 model mappings and any necessary SDK upgrades in Autogen to enable full compatibility.

Which packages was the bug in?

Python Extensions (autogen-ext)

AutoGen library version.

Python dev (main branch)

Other library version.

No response

Model used

gpt-5

Model provider

OpenAI

Other model provider

No response

Python version

3.12

.NET version

None

Operating system

None