Hugging Face

router.huggingface.co

Community

Hugging Face Inference API provides serverless access to thousands of open-source AI models across multiple providers. It supports text generation, image generation, embeddings, classification, and speech recognition through a unified OpenAI-compatible interface.

Auth

api_key

Pricing

free

Spec version

1.0

Base URL

https://router.huggingface.co

Crawl failures

1

Last verified

2026-03-01T11:53:45.000Z

Health

This is a community-maintained manifest. Health monitoring is not available because this service doesn't host its own /.well-known/agent endpoint yet. Learn more about trust levels →

Capabilities

chat_completion

ai-ml

Generate conversational AI responses using any supported open-source language model. OpenAI-compatible endpoint with automatic provider selection.

Detail: https://router.huggingface.co/capabilities/chat_completion

classify_text

ai-ml

Classify text into categories using zero-shot or fine-tuned classification models.

Detail: https://router.huggingface.co/capabilities/classify_text

embed_text

ai-ml

Generate vector embeddings from text inputs using feature extraction models for semantic search and retrieval.

Detail: https://router.huggingface.co/capabilities/embed_text

generate_image

ai-ml

Generate images from text prompts using diffusion models like FLUX and Stable Diffusion.

Detail: https://router.huggingface.co/capabilities/generate_image

generate_text

developer-tools

Generate text continuations from a prompt using open-source language models hosted on Hugging Face infrastructure.

Detail: https://router.huggingface.co/capabilities/generate_text

list_models

ai-ml

List available models with their supported providers, tasks, and configuration details.

Detail: https://router.huggingface.co/capabilities/list_models

transcribe_audio

ai-ml

Convert speech audio files to text using automatic speech recognition models like Whisper.

Detail: https://router.huggingface.co/capabilities/transcribe_audio

Agent Preview

This is what an AI agent sees when it discovers this service via the Gateway:

Service: Hugging Face
Description: Hugging Face Inference API provides serverless access to thousands of open-source AI models across multiple providers. It supports text generation, image generation, embeddings, classification, and speech recognition through a unified OpenAI-compatible interface.
Auth: api_key
Capabilities:
  - chat_completion: Generate conversational AI responses using any supported open-source language model. OpenAI-compatible endpoint with automatic provider selection.
  - classify_text: Classify text into categories using zero-shot or fine-tuned classification models.
  - embed_text: Generate vector embeddings from text inputs using feature extraction models for semantic search and retrieval.
  - generate_image: Generate images from text prompts using diffusion models like FLUX and Stable Diffusion.
  - generate_text: Generate text continuations from a prompt using open-source language models hosted on Hugging Face infrastructure.
  - list_models: List available models with their supported providers, tasks, and configuration details.
  - transcribe_audio: Convert speech audio files to text using automatic speech recognition models like Whisper.