Baseten on Hugging Face Inference Providers 🔥
- ID
- 11584
- Status
- summarized
- Published
- 06 Aug 2026, 8:00 AM
- Fetched
- 06 Aug 2026, 11:48 PM
- Provider
- Hugging Face Blog
- Category
- developer-ai
- Original URL
- https://huggingface.co/blog/baseten
- Source URL
- https://huggingface.co/blog/feed.xml
Summary
- Score
- 4.5
- Created
- 07 Aug 2026, 1:32 PM
- Tags
- Audience
- developersai_agent_usersai_ml_learners
What happened
Baseten is now a supported inference provider on the Hugging Face Hub, offering serverless access to open-weight LLMs like Kimi K3, DeepSeek V4 Flash, and GLM-5.2 for conversational and text-generation tasks. Users can either bring their own Baseten API key or let HF route and bill requests directly to their HF account, with integration into HF's Python (huggingface_hub >= 1.26.1) and JavaScript SDKs plus agent harnesses like Pi, OpenCode, and Hermes Agents.
Why it matters
If you already use HF Inference Providers, you can now add Baseten as a preferred provider in your account settings and compare its latency, pricing, and model availability against existing options like Together or Fireworks for the same open-weight models. No urgent change is required unless you're actively shopping for a new inference backend.
Discussion angle
Compare Baseten's HF-routed billing model (charges to your HF account) versus bring-your-own-key — which is cheaper or easier for a small team shipping an agent in production today?