Baseten joins Hugging Face Inference Providers
Developers can route supported Hub model calls to Baseten from the UI or SDKs.
Why it matters
The addition expands Hugging Face's provider marketplace for serverless inference and gives developers another deployment option without changing much application code. It also reinforces the Hub's role as a routing layer across third-party AI infrastructure providers.
The key points
- 1.Baseten is now available as a Hugging Face Inference Provider.
- 2.Initial support covers conversational and text-generation tasks.
- 3.Calls can use provider keys or route billing through Hugging Face.
Hugging Face said Baseten is now a supported Inference Provider on the Hugging Face Hub. The initial integration supports conversational and text-generation tasks, including access to open-weight models such as Kimi K3, DeepSeek V4 Flash and GLM-5.2. Developers can use Baseten from model pages or through Hugging Face's Python and JavaScript SDKs.
⚡ Try this today
Test Baseten through Hugging Face Inference Providers for supported chat or text-generation workloads before adding provider-specific integration code.
Sources & original reporting
This brief summarizes and links to reporting from the publishers below.
Enjoyed this brief? Get the next one in your inbox.
More in Tools & Open Source
Hacker News debates practical AI use and risks
AI-heavy Hacker News posts span opt-outs, regulation, self-improvement, coding agents and token resale.
AI coding and private AI tools draw Hacker News attention
Posts on coding agents, AI workflows and homomorphic encryption drew active discussion.
AI coding workflows draw broad Hacker News debate
Multiple posts on AI-assisted coding and agent workflows reached Hacker News front pages.