Hugging Face Inference API

api-inference.huggingface.co · AI

AI Bearer Token Free Tier AI Machine Learning NLP

Run inference on 100,000+ open-source AI models — text generation, summarisation, translation, image classification, speech recognition, and more. Free tier with rate limits; $9/mo Pro for higher throughput.

Authentication

Bearer Token Free API token from huggingface.co/settings/tokens. Pass as Authorization: Bearer YOUR_TOKEN.

Sample Requests

POST Text generation

Generate text using Mistral 7B.

https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2

Hover any highlighted part to learn what it does

Headers — extra info sent with the request

Content-Type	application/json
Authorization	Bearer YOUR_TOKEN

Request Body — data you're sending

{
  "inputs": "What is the capital of France?"
}

curl -X POST "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"inputs":"What is the capital of France?"}'

import requests
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
data = {
    "inputs": "What is the capital of France?"
}
response = requests.post(
    "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2",
    headers=headers,
    json=data,
)
print(response.json())

const url = 'https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2';

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_ACCESS_TOKEN'
  },
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
  "inputs": "What is the capital of France?"
}),
}); 
const data = await response.json();
console.log(data);

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
	"encoding/json"
)

func main() {
	targetURL := "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
	jsonData, _ := json.Marshal({"inputs":"What is the capital of France?"})
	req, _ := http.NewRequest("POST", targetURL, bytes.NewBuffer(jsonData))
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer YOUR_ACCESS_TOKEN")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	body, _ := io.ReadAll(resp.Body)
	fmt.Println(string(body))
}

require "net/http"
require "json"

uri = URI("https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2")

http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = uri.scheme == "https"

req = Net::HTTP::Post.new(uri)
req["Content-Type"] = "application/json"
req["Authorization"] = "Bearer YOUR_ACCESS_TOKEN"
req["Content-Type"] = "application/json"
req.body = "{\"inputs\":\"What is the capital of France?\"}"

res = http.request(req)
puts JSON.parse(res.body)

<?php
$url = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2";
$opts = ["http" => [
    "method" => "POST",
    "header" => implode("\r\n", [
        "Content-Type: application/json",
        "Authorization: Bearer YOUR_ACCESS_TOKEN",
        "Content-Type: application/json"
    ]),
    "content" => json_encode({"inputs":"What is the capital of France?"}),
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));

POST Sentiment analysis

Classify sentiment of a text.

https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english

Hover any highlighted part to learn what it does

Headers — extra info sent with the request

Content-Type	application/json
Authorization	Bearer YOUR_TOKEN

Request Body — data you're sending

{
  "inputs": "This product is amazing!"
}

curl -X POST "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"inputs":"This product is amazing!"}'

import requests
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
data = {
    "inputs": "This product is amazing!"
}
response = requests.post(
    "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english",
    headers=headers,
    json=data,
)
print(response.json())

const url = 'https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english';

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_ACCESS_TOKEN'
  },
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
  "inputs": "This product is amazing!"
}),
}); 
const data = await response.json();
console.log(data);

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
	"encoding/json"
)

func main() {
	targetURL := "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english"
	jsonData, _ := json.Marshal({"inputs":"This product is amazing!"})
	req, _ := http.NewRequest("POST", targetURL, bytes.NewBuffer(jsonData))
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer YOUR_ACCESS_TOKEN")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	resp, _ := client.Do(req)
	defer resp.Body.Close()
	body, _ := io.ReadAll(resp.Body)
	fmt.Println(string(body))
}

require "net/http"
require "json"

uri = URI("https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english")

http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = uri.scheme == "https"

req = Net::HTTP::Post.new(uri)
req["Content-Type"] = "application/json"
req["Authorization"] = "Bearer YOUR_ACCESS_TOKEN"
req["Content-Type"] = "application/json"
req.body = "{\"inputs\":\"This product is amazing!\"}"

res = http.request(req)
puts JSON.parse(res.body)

<?php
$url = "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english";
$opts = ["http" => [
    "method" => "POST",
    "header" => implode("\r\n", [
        "Content-Type: application/json",
        "Authorization: Bearer YOUR_ACCESS_TOKEN",
        "Content-Type: application/json"
    ]),
    "content" => json_encode({"inputs":"This product is amazing!"}),
]];
$ctx = stream_context_create($opts);
$res = file_get_contents($url, false, $ctx);
print_r(json_decode($res, true));

Postman Setup Guide

Get Postman ↗

Create a free account at huggingface.co
Go to Settings → Access Tokens → New Token (Read)
Set Authorization: Bearer YOUR_TOKEN
Replace the model name in the URL with any model from huggingface.co/models
First request may take 20s to load model — retry if you get a 503

Open documentation ↗