docs(openai): add Auxen as OpenAI-compatible provider example

[ai-auxen]

Adds an Auxen section to `docs/models/openai.md` under "OpenAI-compatible Models", positioned before the existing DeepSeek entry.

Auxen hosts per-customer dedicated LLM endpoints (Llama 3.1/3.2, Qwen 2.5, Mistral, Gemma 2, Mixtral, Phi-3, Command R) with an OpenAI-compatible `/v1/chat/completions` API. Each instance is a dedicated GPU billed per-minute of runtime.

Docs-only on purpose

Unlike the existing named providers (Fireworks, Together, DeepSeek, etc.) which have fixed shared base URLs, every Auxen instance has its own per-instance base URL of the form `https://api.auxen.ai/v1/inst_xxx/v1\`. There is no shared default endpoint to encode in a dedicated provider class, so the docs use the generic `OpenAIProvider` with explicit `base_url` and `api_key` — same shape the docs already recommend for arbitrary OpenAI-compatible endpoints.

Happy to also add a dedicated `AuxenProvider` class (that takes `base_url` and `api_key` as required arguments) if the team would prefer that shape — let me know.

Companion PRs (Auxen distribution series)

• BerriAI/litellm#28532 — LiteLLM provider
• vercel/ai#15536 — Vercel AI SDK community provider
• langchain-ai/docs#4146 — LangChain docs (Python + JS)
• run-llama/llama_index#21764 — LlamaIndex Python
• continuedev/continue#12473 — Continue.dev provider
• cline/cline#10988 — Cline OpenAI-compatible quickstart
• crewAIInc/crewAI#5911 — CrewAI provider config
• Helicone/helicone#5685 — Helicone gateway
• langfuse/langfuse-docs#2990 — Langfuse provider page
• npm: `@auxen/ai-sdk-provider` (live)

AI agent (Claude) assisted in drafting this PR.

[dsfaccini]

David's AICA here: Thanks for taking the time to put this together. We don't feel comfortable using the Pydantic AI docs to promote or catalogue third-party OpenAI-compatible services, since inclusion there can read as an endorsement or preferred integration. This can already be used with the existing OpenAI-compatible provider configuration, and you're welcome to keep setup instructions in your own docs for users who want to connect it to Pydantic AI. Closing as not planned.