Baseten Joins Hugging Face as an Inference Provider, Bringing Popular AI Models to More Developers
Developers can now run open-weight AI models through Baseten directly from the Hugging Face Hub, with no extra markup on costs and two billing paths to choose from.
Key points
- Hugging Face added Baseten as a supported Inference Provider on its model Hub, announced in 2025.
- Baseten initially supports conversational and text-generation tasks, including models such as Kimi K3 and DeepSeek V4 Flash.
- Hugging Face PRO subscribers receive $2 in monthly inference credits usable across all providers, including Baseten.
- Developers can authenticate with a single Hugging Face token; Hugging Face routes the request to Baseten automatically.
- Hugging Face charges no markup on routed requests, passing provider costs through at standard rates.
Hugging Face, the platform where researchers and companies share AI models, has added Baseten to its list of Inference Providers. An Inference Provider is a service that actually runs an AI model and sends back a result. Before this change, developers who wanted to use Baseten-hosted models had to set that up separately. Now they can do it straight from the Hugging Face model page.
Baseten is an AI infrastructure company. Think of it as a platform that handles all the server work so a developer can call a powerful AI model, like a large language model (the technology that powers chatbots such as ChatGPT), with a few lines of code instead of managing computers themselves.
What models are available right now?
At launch, Baseten supports text-generation and conversational tasks on Hugging Face, including open-weight models, meaning models whose underlying design is publicly available. The initial lineup includes Kimi K3, DeepSeek V4 Flash, and GLM-5.2. More model types are coming.
| Model | Type | Status |
|---|---|---|
| Kimi K3 | Open-weight LLM | Available now |
| DeepSeek V4 Flash | Open-weight LLM | Available now |
| GLM-5.2 | Open-weight LLM | Available now |
| Additional task types | Text-to-speech, others | Rolling out soon |
How does billing work?
There are two paths. If you supply your own Baseten API key (a private code that identifies your account), charges go directly to your Baseten account. If you authenticate through Hugging Face instead, the cost appears on your Hugging Face bill at the standard provider rate. Hugging Face adds no markup.
Hugging Face PRO subscribers get $2 in inference credits each month, usable across any supported provider, including Baseten.
Free, signed-in Hugging Face users get a small quota at no charge. Past that limit, upgrading to PRO unlocks the credits and higher usage limits.
Should ordinary users care about this?
If you build apps or experiment with AI tools, this matters: one account, one token, access to several providers without juggling separate API keys. For people who just use finished apps, the change is invisible but may quietly improve reliability, since developers can now switch providers without rewriting their code.
The integration also works inside AI agent tools, software that can carry out multi-step tasks on its own, such as Pi, OpenCode, and Hermes Agents, so models running on Baseten slot into those workflows automatically.
Common questions
Do I need a Baseten account to try this?
No. You can authenticate with your Hugging Face token and the request routes through Hugging Face. A Baseten account is only needed if you want to use your own Baseten API key and bill directly to that account.
Is the Hugging Face Python or JavaScript library compatible?
Yes. The huggingface_hub Python library at version 1.26.1 or higher and the @huggingface/inference JavaScript package both support Baseten as of this launch.
