Hi Hugging Face team ![]()
We’d like to register OpenInfer as an Inference Provider.
OpenInfer provides a production OpenAI-compatible inference API focused on high-performance, cost-efficient model serving across heterogeneous infrastructure.
Current API
- API Base:
https://api.openinfer.ai/v1 - Chat Completions:
/v1/chat/completions - Models:
/v1/models - Bearer authentication
- SSE streaming
- Token usage reporting (streaming and non-streaming)
Current deployment
- Initial model:
@oi/Llama-3.2-1B-Instruct - Text generation
- Additional models will be added as they complete validation.
Our endpoints are live, and we’re interested in becoming an official Hugging Face Inference Provider. We’d appreciate guidance on the next steps and any technical or commercial onboarding requirements.
Website: https://openinfer.io
Thanks—we look forward to working with the Hugging Face team.