Add CerebrasModel

[sebastiand-cerebras]

• Add CerebrasProvider using OpenAI SDK for Cerebras's OpenAI-compatible API
• Support for Llama 3.3, Qwen 3, GPT-OSS, and GLM
• Add cerebras optional dependency group
• Add documentation with usage examples

---

Thank you for reviewing this.

[DouweM]

@sebastiand-cerebras Hey Seb, Cerebras is already documented at https://ai.pydantic.dev/models/openai/#cerebras as it uses the OpenAIChatModel. So far, we've reserved dedicated pages under docs/models for those providers that have dedicated model classes that use their own API/SDK or implement additional functionality not provided by the basic OpenAI Chat Completions API spec and class.

In #3089, we're implementing a new OpenRouterModel as a subclass of OpenAIChatModel that enables OpenRouter-specific features.

Would it be an option to do same thing for Cerebras, implementing support for any Cerebras-specific additions to the chat completions API?

PS. We have a private Slack channel with Cerebras; happy to discuss this more there as well

[sebastiand-cerebras]

Thank you so much for your feedback! I did add these:

• Create a Cerebras model subclass of the OpenAI Chat model.
• Set up Cerebras-specific code paths, similar to how OpenRouter handles them.
• Remove SDK-related code.
• Add a separate optional dependency group for OpenAI by Cerebras.

[DouweM]

Thanks @sebastiand-cerebras, just one tiny thing and I'll merge!

[DouweM]

@sebastiand-cerebras Please have a look at the linter failure; we'll likely need a pyright: ignore[...] in the test!