npm install @huggingface/inference

pnpm add @huggingface/inference

yarn add @huggingface/inference

// esm.sh
import { InferenceClient } from "https://esm.sh/@huggingface/inference";
// or npm:
import { InferenceClient } from "npm:@huggingface/inference";

import { InferenceClient } from '@huggingface/inference';

const hf = new InferenceClient('your access token');

const accessToken = "hf_..."; // Either a HF access token, or an API key from the third-party provider (Replicate in this example)

const client = new InferenceClient(accessToken);
await client.textToImage({
  provider: "replicate",
  model:"black-forest-labs/Flux.1-dev",
  inputs: "A black forest cake"
})

import { textGeneration } from "@huggingface/inference";

await textGeneration({
  accessToken: "hf_...",
  model: "model_or_endpoint",
  inputs: ...,
  parameters: ...
})

import { InferenceClient } from "@huggingface/inference";
import {
  InferenceClientError,
  InferenceClientInputError,
  InferenceClientProviderApiError,
  InferenceClientProviderOutputError,
  InferenceClientHubApiError,
} from "@huggingface/inference";

const client = new InferenceClient();

try {
  const result = await client.textGeneration({
    model: "gpt2",
    inputs: "Hello, I'm a language model",
  });
} catch (error) {
  if (error instanceof InferenceClientProviderApiError) {
    // Handle API errors (e.g., rate limits, authentication issues)
    console.error("Provider API Error:", error.message);
    console.error("HTTP Request details:", error.httpRequest);
    console.error("HTTP Response details:", error.httpResponse);
  } else if (error instanceof InferenceClientHubApiError) {
    // Handle API errors (e.g., rate limits, authentication issues)
    console.error("Hub API Error:", error.message);
    console.error("HTTP Request details:", error.httpRequest);
    console.error("HTTP Response details:", error.httpResponse);
  } else if (error instanceof InferenceClientProviderOutputError) {
    // Handle malformed responses from providers
    console.error("Provider Output Error:", error.message);
  } else if (error instanceof InferenceClientInputError) {
    // Handle invalid input parameters
    console.error("Input Error:", error.message);
  } else {
    // Handle unexpected errors
    console.error("Unexpected error:", error);
  }
}

/// Catch all errors from @huggingface/inference
try {
  const result = await client.textGeneration({
    model: "gpt2",
    inputs: "Hello, I'm a language model",
  });
} catch (error) {
  if (error instanceof InferenceClientError) {
    // Handle errors from @huggingface/inference
    console.error("Error from InferenceClient:", error);
  } else {
    // Handle unexpected errors
    console.error("Unexpected error:", error);
  }
}

await hf.textGeneration({
  model: 'mistralai/Mixtral-8x7B-v0.1',
  provider: "together",
  inputs: 'The answer to the universe is'
})

for await (const output of hf.textGenerationStream({
  model: "mistralai/Mixtral-8x7B-v0.1",
  provider: "together",
  inputs: 'repeat "one two three four"',
  parameters: { max_new_tokens: 250 }
})) {
  console.log(output.token.text, output.generated_text);
}

// Non-streaming API
const out = await hf.chatCompletion({
  model: "Qwen/Qwen3-32B",
  provider: "cerebras",
  messages: [{ role: "user", content: "Hello, nice to meet you!" }],
  max_tokens: 512,
  temperature: 0.1,
});

// Streaming API
let out = "";
for await (const chunk of hf.chatCompletionStream({
  model: "Qwen/Qwen3-32B",
  provider: "cerebras",
  messages: [
    { role: "user", content: "Can you help me solve an equation?" },
  ],
  max_tokens: 512,
  temperature: 0.1,
})) {
  if (chunk.choices && chunk.choices.length > 0) {
    out += chunk.choices[0].delta.content;
  }
}

await hf.featureExtraction({
  model: "sentence-transformers/distilbert-base-nli-mean-tokens",
  inputs: "That is a happy person",
});

await hf.fillMask({
  model: 'bert-base-uncased',
  inputs: '[MASK] world!'
})

await hf.summarization({
  model: 'facebook/bart-large-cnn',
  inputs:
    'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930.',
  parameters: {
    max_length: 100
  }
})

await hf.questionAnswering({
  model: 'deepset/roberta-base-squad2',
  inputs: {
    question: 'What is the capital of France?',
    context: 'The capital of France is Paris.'
  }
})

await hf.tableQuestionAnswering({
  model: 'google/tapas-base-finetuned-wtq',
  inputs: {
    query: 'How many stars does the transformers repository have?',
    table: {
      Repository: ['Transformers', 'Datasets', 'Tokenizers'],
      Stars: ['36542', '4512', '3934'],
      Contributors: ['651', '77', '34'],
      'Programming language': ['Python', 'Python', 'Rust, Python and NodeJS']
    }
  }
})

await hf.textClassification({
  model: 'distilbert-base-uncased-finetuned-sst-2-english',
  inputs: 'I like you. I love you.'
})

await hf.tokenClassification({
  model: 'dbmdz/bert-large-cased-finetuned-conll03-english',
  inputs: 'My name is Sarah Jessica Parker but you can call me Jessica'
})

await hf.translation({
  model: 't5-base',
  inputs: 'My name is Wolfgang and I live in Berlin'
})

await hf.translation({
  model: 'facebook/mbart-large-50-many-to-many-mmt',
  inputs: textToTranslate,
  parameters: {
  "src_lang": "en_XX",
  "tgt_lang": "fr_XX"
 }
})

await hf.zeroShotClassification({
  model: 'facebook/bart-large-mnli',
  inputs: [
    'Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!'
  ],
  parameters: { candidate_labels: ['refund', 'legal', 'faq'] }
})

await hf.sentenceSimilarity({
  model: 'sentence-transformers/paraphrase-xlm-r-multilingual-v1',
  inputs: {
    source_sentence: 'That is a happy person',
    sentences: [
      'That is a happy dog',
      'That is a very happy person',
      'Today is a sunny day'
    ]
  }
})

await hf.textRanking({
  model: 'cross-encoder/ettin-reranker-68m-v1',
  inputs: {
    query: 'Which planet is known as the Red Planet?',
    texts: [
      "Venus is often called Earth's twin because of its similar size and proximity.",
      'Mars, known for its reddish appearance, is often referred to as the Red Planet.',
      'Jupiter, the largest planet in our solar system, has a prominent red spot.',
      'Saturn, famous for its rings, is sometimes mistaken for the Red Planet.'
    ]
  }
})

await hf.automaticSpeechRecognition({
  model: 'facebook/wav2vec2-large-960h-lv60-self',
  data: readFileSync('test/sample1.flac')
})

await hf.audioClassification({
  model: 'superb/hubert-large-superb-er',
  data: readFileSync('test/sample1.flac')
})

await hf.textToSpeech({
  model: 'espnet/kan-bayashi_ljspeech_vits',
  inputs: 'Hello world!'
})

await hf.audioToAudio({
  model: 'speechbrain/sepformer-wham',
  data: readFileSync('test/sample1.flac')
})

await hf.imageClassification({
  data: readFileSync('test/cheetah.png'),
  model: 'google/vit-base-patch16-224'
})

await hf.objectDetection({
  data: readFileSync('test/cats.png'),
  model: 'facebook/detr-resnet-50'
})

await hf.imageSegmentation({
  data: readFileSync('test/cats.png'),
  model: 'facebook/detr-resnet-50-panoptic'
})

await hf.imageToText({
  data: readFileSync('test/cats.png'),
  model: 'nlpconnect/vit-gpt2-image-captioning'
})

await hf.textToImage({
  model: 'black-forest-labs/FLUX.1-dev',
  inputs: 'a picture of a green bird'
})

await hf.imageToImage({
  inputs: new Blob([readFileSync("test/stormtrooper_depth.png")]),
  parameters: {
    prompt: "elmo's lecture",
  },
  model: "lllyasviel/sd-controlnet-depth",
});

await hf.zeroShotImageClassification({
  model: 'openai/clip-vit-large-patch14-336',
  inputs: {
    image: await (await fetch('https://placekitten.com/300/300')).blob()
  },
  parameters: {
    candidate_labels: ['cat', 'dog']
  }
})

await hf.visualQuestionAnswering({
  model: 'dandelin/vilt-b32-finetuned-vqa',
  inputs: {
    question: 'How many cats are lying down?',
    image: await (await fetch('https://placekitten.com/300/300')).blob()
  }
})

await hf.documentQuestionAnswering({
  model: 'impira/layoutlm-document-qa',
  inputs: {
    question: 'Invoice number?',
    image: await (await fetch('https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png')).blob(),
  }
})

await hf.tabularRegression({
  model: "scikit-learn/Fish-Weight",
  inputs: {
    data: {
      "Height": ["11.52", "12.48", "12.3778"],
      "Length1": ["23.2", "24", "23.9"],
      "Length2": ["25.4", "26.3", "26.5"],
      "Length3": ["30", "31.2", "31.1"],
      "Species": ["Bream", "Bream", "Bream"],
      "Width": ["4.02", "4.3056", "4.6961"]
    },
  },
})

await hf.tabularClassification({
  model: "vvmnnnkv/wine-quality",
  inputs: {
    data: {
      "fixed_acidity": ["7.4", "7.8", "10.3"],
      "volatile_acidity": ["0.7", "0.88", "0.32"],
      "citric_acid": ["0", "0", "0.45"],
      "residual_sugar": ["1.9", "2.6", "6.4"],
      "chlorides": ["0.076", "0.098", "0.073"],
      "free_sulfur_dioxide": ["11", "25", "5"],
      "total_sulfur_dioxide": ["34", "67", "13"],
      "density": ["0.9978", "0.9968", "0.9976"],
      "pH": ["3.51", "3.2", "3.23"],
      "sulphates": ["0.56", "0.68", "0.82"],
      "alcohol": ["9.4", "9.8", "12.6"]
    },
  },
})

// Chat Completion Example
const MISTRAL_KEY = process.env.MISTRAL_KEY;
const hf = new InferenceClient(MISTRAL_KEY, {
  endpointUrl: "https://api.mistral.ai",
});
const stream = hf.chatCompletionStream({
  model: "mistral-tiny",
  messages: [{ role: "user", content: "Complete the equation one + one = , just the answer" }],
});
let out = "";
for await (const chunk of stream) {
  if (chunk.choices && chunk.choices.length > 0) {
    out += chunk.choices[0].delta.content;
    console.log(out);
  }
}

import { InferenceClient } from '@huggingface/inference';

const hf = new InferenceClient("hf_xxxxxxxxxxxxxx", {
	endpointUrl: "https://j3z5luu0ooo76jnl.us-east-1.aws.endpoints.huggingface.cloud/v1/",
});

const response = await hf.chatCompletion({
	messages: [
		{
			role: "user",
			content: "What is the capital of France?",
		},
	],
});

console.log(response.choices[0].message.content);

const hf = new InferenceClient("hf_xxxxxxxxxxxxxx", {
	endpointUrl: "https://j3z5luu0ooo76jnl.us-east-1.aws.endpoints.huggingface.cloud/v1/",
});

const response = await hf.chatCompletion(
	{
		messages: [
			{
				role: "user",
				content: "What is the capital of France?",
			},
		],
	},
	{
		retry_on_error: false,
	}
);

import { InferenceClient } from '@huggingface/inference';

const hf = new InferenceClient(undefined, {
	endpointUrl: "http://localhost:8080",
});

const response = await hf.chatCompletion({
	messages: [
		{
			role: "user",
			content: "What is the capital of France?",
		},
	],
});

console.log(response.choices[0].message.content);

HF_TOKEN="your access token" pnpm run test