Post by DeepInfra

🤝 DeepInfra × Hugging Face — official today. Starting today, every developer on the Hub can run inference against our catalog of 100+ open-weight models without leaving their existing workflow — directly from Hugging Face model pages, through our OpenAI-compatible router (use it with any OpenAI SDK), or via the Hugging Face SDKs in Python and JavaScript. Two ways to use it: • Drop your DeepInfra API key into your HF provider settings — requests go straight to us, billed on your DeepInfra account. • Or just use your Hugging Face token and let HF route to us. PRO users get $2 of inference credits every month to spend across providers. Same OpenAI-compatible API, same low per-token pricing, no markup. The only thing that changes in your code is appending :deepinfra to the model name. Inference economics are still the deciding factor for most teams trying to ship AI in production. Putting our serverless stack one click away from every developer on Hugging Face is the right next step. 🔗 Try it: https://lnkd.in/gufCKwkh 📘 Docs: https://lnkd.in/gCxhJZxt #AI #OpenSource #Inference #DeepInfra #HuggingFace