### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

OpenInfer would like to contribute a native LiteLLM provider integration. OpenInfer provides a production OpenAI-compatible inference API focused on cost-efficient, high-performance inference across heterogeneous compute infrastructure.

Current capabilities include: OpenAI-compatible /v1/chat/completions /v1/models endpoint Bearer authentication Streaming (SSE) Token usage reporting Enterprise deployments and dedicated infrastructure

A native provider would allow LiteLLM users to configure OpenInfer without relying on the generic OpenAI-compatible provider, providing a simpler setup and better user experience.

API Base https://api.openinfer.ai/v1

Website https://openinfer.io We're happy to contribute the provider implementation and work with the LiteLLM team on integration.

### Motivation, pitch

OpenInfer provides a production OpenAI-compatible inference API focused on delivering high-performance, cost-efficient AI inference across heterogeneous compute infrastructure. A native LiteLLM provider would allow developers to use OpenInfer as a fi…