Hugging Face

Hugging Face Natural Language Processing API

NLP tasks including text generation, classification, and translation

GitHub OpenAPI
Business capability
Artificial Intelligence Management BC-610.60

Operations 11

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /models/{model_id} Run inference on any Hub model · Run Inference on a Model #
Ask an LLM
“Can I call any model hosted on the Hub with a generic inference request?”
“Does the input and output format change depending on a model's pipeline task?”
Tell an agent
Run inference on model {model_id} with input {inputs}.
Send {inputs} to {model_id} with task parameters {parameters}.
POST /pipeline/{task} Run inference by task with a recommended model · Run Inference by Task Pipeline #
Ask an LLM
“Can I name just a task like summarization and let Hugging Face pick the best model?”
“Which pipeline tasks can I run without choosing a model myself?”
Tell an agent
Run the {task} pipeline on {inputs}.
Use the recommended model for {task} to process {inputs}.
POST /models/{model_id}/text-generation Continue a prompt with a language model · Text Generation Inference #
Ask an LLM
“Can I generate text from a prompt with a specific Hub model and control temperature and top_p?”
“Is there a way to cap max new tokens or penalize repetition in serverless text generation?”
Tell an agent
Continue the prompt {inputs} with model {model_id}.
Generate text from {inputs} on {model_id} using parameters {parameters}.
POST /models/{model_id}/text-classification Classify text, such as sentiment · Text Classification Inference #
Ask an LLM
“Can I tell whether a review is positive or negative with a sentiment model?”
“What labels and scores does text classification return?”
Tell an agent
Classify the sentiment of {inputs} with model {model_id}.
Label {inputs} using text classifier {model_id}.
POST /models/{model_id}/question-answering Extract an answer from a context passage · Question Answering Inference #
Ask an LLM
“Can a model pull the answer to a question out of a passage I provide?”
“Which task finds an answer span inside my own document text?”
Tell an agent
Answer the question in {inputs} from its context using model {model_id}.
Extract the answer span for {inputs} with QA model {model_id}.
POST /models/{model_id}/summarization Summarize a long text · Text Summarization Inference #
Ask an LLM
“Can I shorten a long article into a brief summary with a Hub model?”
“Is there a way to control summary length through task parameters?”
Tell an agent
Summarize {inputs} with model {model_id}.
Write a shorter version of {inputs} using {model_id} and parameters {parameters}.
POST /models/{model_id}/translation Translate text between languages · Translation Inference #
Ask an LLM
“Can I translate a sentence into another language with a translation model?”
“Which serverless task should I use to translate text with a model I pick?”
Tell an agent
Translate {inputs} with model {model_id}.
Run translation model {model_id} on {inputs}.
POST /models/{model_id}/fill-mask Fill a masked word in a sentence · Fill Mask Inference #
Ask an LLM
“Can a model guess the missing word where I put a [MASK] token?”
“What candidates and scores come back for a masked token?”
Tell an agent
Fill the [MASK] in {inputs} using model {model_id}.
Predict the masked word in {inputs} with {model_id}.
POST /models/{model_id}/feature-extraction Extract embeddings with a chosen Hub model · Feature Extraction Inference #
Ask an LLM
“Can I get raw feature vectors from a specific Hub model by calling its feature-extraction task?”
“Which serverless model task returns dense vector representations for text?”
Tell an agent
Extract features for {inputs} using model {model_id}.
Get the feature-extraction vectors of {inputs} from {model_id}.
POST /models/{model_id}/zero-shot-classification Classify text into labels you supply · Zero-shot Classification Inference #
Ask an LLM
“Can I classify text into my own categories without training a model?”
“Where do I pass the candidate labels for zero-shot classification?”
Tell an agent
Classify {inputs} into the candidate labels in {parameters} with model {model_id}.
Run zero-shot classification of {inputs} on {model_id} using labels {parameters}.
POST /models/{model_id}/sentence-similarity Score similarity between sentences · Sentence Similarity Inference #
Ask an LLM
“Can I measure how similar one sentence is to a list of other sentences?”
“Which task returns similarity scores between a source sentence and targets?”
Tell an agent
Compare the source and target sentences in {inputs} with model {model_id}.
Score sentence similarity for {inputs} using {model_id}.

Documentation

📖
Documentation
https://huggingface.co/docs/api-inference/index
📖
Authentication
https://huggingface.co/docs/api-inference/quicktour#authentication
📖
GettingStarted
https://huggingface.co/docs/api-inference/quicktour
📖
RateLimits
https://huggingface.co/docs/api-inference/en/rate-limits
📖
Documentation
https://huggingface.co/docs/hub/api
📖
Authentication
https://huggingface.co/docs/hub/security-tokens
📖
RateLimits
https://huggingface.co/docs/hub/en/rate-limits
📖
Documentation
https://huggingface.co/docs/inference-endpoints/api_reference
📖
GettingStarted
https://huggingface.co/docs/inference-endpoints/index
📖
Documentation
https://huggingface.co/docs/inference-providers/en/index
📖
APIReference
https://huggingface.co/docs/inference-providers/en/tasks/index
📖
GettingStarted
https://huggingface.co/docs/inference-providers/en/guides/first-api-call
📖
Documentation
https://huggingface.co/docs/dataset-viewer/index
📖
GettingStarted
https://huggingface.co/docs/dataset-viewer/en/quick_start
📖
Documentation
https://huggingface.co/docs/text-generation-inference/en/index
📖
APIReference
https://huggingface.co/docs/text-generation-inference/en/reference/api_reference
📖
GettingStarted
https://huggingface.co/docs/text-generation-inference/quicktour
📖
Documentation
https://huggingface.co/docs/text-generation-inference/en/messages_api

Specifications

⚙
OpenAPI
https://artifacts.apis.io/hugging-face/openapi/hugging-face-natural-language-processing-api-openapi.yml

SDKs

📦
GitHubRepository
https://github.com/huggingface/dataset-viewer
📦
GitHubRepository
https://github.com/huggingface/text-generation-inference

Other Resources

🔗
FAQ
https://huggingface.co/docs/api-inference/faq
🔗
SDKs
https://huggingface.co/docs/huggingface_hub/index
🔗
SDKs
https://huggingface.co/docs/huggingface.js/hub/README
🔗
Pricing
https://huggingface.co/pricing#inference-endpoints
🔗
Pricing
https://huggingface.co/docs/inference-providers/pricing
🔗
Models
https://huggingface.co/inference/models

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/hugging-face:hugging-face-natural-language-processing-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

hugging-face-natural-language-processing-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Hugging Face Inference Natural Language Processing API
  description: Run inference on 200,000+ machine learning models hosted on the Hugging Face Hub with a simple HTTP request. Supports text generation, image classification, object detection, speech recognition, and many more tasks.
  version: 1.0.0
  termsOfService: https://huggingface.co/terms-of-service
  contact:
    name: Hugging Face Support
    url: https://huggingface.co/support
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://api-inference.huggingface.co
  description: Hugging Face Inference API production server
security:
- bearerAuth: []
tags:


# --- truncated at 32 KB (32 KB total) ---
# Full source: https://artifacts.apis.io/hugging-face/openapi/hugging-face-natural-language-processing-api-openapi.yml