---
title: "DeepInfra on Hugging Face Inference Providers 🔥"
description: "DeepInfra is now a supported Inference Provider on the Hugging Face Hub, adding its serverless inference platform and catalog of more than 100 models to model pages and client integrations. The initial integration supports conversational and text-generation tasks, with access to open-weight LLMs including DeepSeek V4, Kimi-K2.6, and GLM-5.1; support for text-to-image, text-to-video, embeddings, and other tasks will roll out soon. Users can configure provider API keys and preferences in account settings, or authenticate with a Hugging Face token so requests are routed through Hugging Face, including from the Python and JavaScript SDKs and supported agent harnesses. Direct requests are billed by the provider, while routed requests use standard provider API rates without additional markup, and Hugging Face PRO users receive $2 of monthly Inference credits."
---

# DeepInfra on Hugging Face Inference Providers 🔥

[Hugging Face](https://yomu.fyi/company/hugging-face) · Aray Sultanbekova, Shang-Pin, Utemuratov, Yessen K, Oguz Vuruskaner, Célina Hanouti, Simon Brandeis, Lucain Pouget · Apr 29, 2026

**Type:** Announcement

## Summary

DeepInfra is now a supported Inference Provider on the Hugging Face Hub, adding its serverless inference platform and catalog of more than 100 models to model pages and client integrations. The initial integration supports conversational and text-generation tasks, with access to open-weight LLMs including DeepSeek V4, Kimi-K2.6, and GLM-5.1; support for text-to-image, text-to-video, embeddings, and other tasks will roll out soon. Users can configure provider API keys and preferences in account settings, or authenticate with a Hugging Face token so requests are routed through Hugging Face, including from the Python and JavaScript SDKs and supported agent harnesses. Direct requests are billed by the provider, while routed requests use standard provider API rates without additional markup, and Hugging Face PRO users receive $2 of monthly Inference credits.

## Context

The integration is presented as a way to expand serverless inference options on Hugging Face and make DeepInfra's catalog of more than 100 models available with minimal setup.

## Approach / What changed

DeepInfra is integrated into Hugging Face model pages, account settings, the Python and JavaScript client SDKs, and supported agent harnesses. Users can supply provider API keys for direct calls or authenticate through Hugging Face for routed requests, while selecting provider preferences in their account settings.

## Takeaways

- The initial DeepInfra integration supports conversational and text-generation tasks, including access to open-weight models such as DeepSeek V4, Kimi-K2.6, and GLM-5.1.
- Requests can use a user's own DeepInfra key and be billed by DeepInfra, or be routed through Hugging Face with charges applied to the user's Hugging Face account.
- DeepInfra is available through huggingface\_hub version 1.11.2 or later for Python and @huggingface/inference for JavaScript, as well as several listed agent harnesses.

**Tags:** [LLMs](https://yomu.fyi/topic/llm), [Python](https://yomu.fyi/topic/python), [Serverless](https://yomu.fyi/topic/serverless)

- Source: [Hugging Face](https://huggingface.co/blog/inference-providers-deepinfra)
- Source URL: https://huggingface.co/blog/inference-providers-deepinfra
- Ingested by Yomu: 2026-08-29T01:48:31.794Z

[Read original post](https://huggingface.co/blog/inference-providers-deepinfra)