DeepInfra Native API

The DeepInfra Native API gives you access to every model we provide, including model types not covered by the OpenAI-compatible API: image generation, speech recognition, object detection, token classification, fill mask, image classification, zero-shot image classification, and text classification. For LLMs and embeddings, the OpenAI-compatible API is simpler and recommended. Use the native API when you need model types beyond LLMs/embeddings, or when you need features like webhooks or log probabilities. The base endpoint is:

https://api.deepinfra.com/v1/inference/{model_name}

JavaScript client

npm install deepinfra

Text Generation (LLMs)

import { TextGeneration } from "deepinfra";

const client = new TextGeneration(
  "https://api.deepinfra.com/v1/inference/deepseek-ai/DeepSeek-V3",
  "$DEEPINFRA_TOKEN"
);

const res = await client.generate({
  input: "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
  stop: ["<|eot_id|>"]
});

console.log(res.results[0].generated_text);
console.log(res.inference_status.tokens_input, res.inference_status.tokens_generated);

curl "https://api.deepinfra.com/v1/inference/deepseek-ai/DeepSeek-V3" \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
   -d '{
     "input": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
     "stop": ["<|eot_id|>"],
     "stream": false
   }'

Embeddings

import { Embeddings } from "deepinfra";

const client = new Embeddings("Qwen/Qwen3-Embedding-8B", "$DEEPINFRA_TOKEN");
const output = await client.generate({
  inputs: [
    "What is the capital of France?",
    "What is the capital of Germany?",
  ],
});
console.log(output.embeddings[0]);

curl -X POST \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -F 'inputs=["I like chocolate"]' \
    'https://api.deepinfra.com/v1/inference/Qwen/Qwen3-Embedding-8B'

Image Generation

import { TextToImage } from "deepinfra";
import { createWriteStream } from "fs";
import { Readable } from "stream";

const model = new TextToImage("stabilityai/stable-diffusion-2-1", "$DEEPINFRA_TOKEN");
const response = await model.generate({
  prompt: "a burger with a funny hat on the beach",
});

const result = await fetch(response.images[0]);
if (result.ok && result.body) {
  Readable.fromWeb(result.body).pipe(createWriteStream("image.png"));
}

curl "https://api.deepinfra.com/v1/inference/stabilityai/stable-diffusion-2-1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
  -d '{"prompt": "a burger with a funny hat on the beach"}'

Speech Recognition

curl -X POST \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -F audio=@audio.mp3 \
    'https://api.deepinfra.com/v1/inference/openai/whisper-large'

Object Detection

curl -X POST \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -F image=@image.jpg \
    'https://api.deepinfra.com/v1/inference/hustvl/yolos-small'

Token Classification

curl -X POST \
    -d '{"input": "My name is John Doe and I live in San Francisco."}' \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -H 'Content-Type: application/json' \
    'https://api.deepinfra.com/v1/inference/Davlan/bert-base-multilingual-cased-ner-hrl'

Fill Mask

curl -X POST \
    -d '{"input": "I need my [MASK] right now!"}' \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -H 'Content-Type: application/json' \
    'https://api.deepinfra.com/v1/inference/bert-base-cased'

Image Classification

curl -X POST \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -F image=@image.jpg \
    'https://api.deepinfra.com/v1/inference/google/vit-base-patch16-224'

Zero-Shot Image Classification

curl -X POST \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -F image=@image.jpg \
    -F 'candidate_labels=["dog", "cat", "car", "horse", "person"]' \
    'https://api.deepinfra.com/v1/inference/openai/clip-vit-base-patch32'

Text Classification

curl -X POST \
    -d '{"input": "Nvidia announces new AI chips months after latest launch"}' \
    -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
    -H 'Content-Type: application/json' \
    'https://api.deepinfra.com/v1/inference/ProsusAI/finbert'

HTTP / other languages

The native API is plain HTTP — you can use it from any language (Go, C#, Java, PHP, Ruby, C++, etc.) without any SDK dependency.

​JavaScript client

​Text Generation (LLMs)

​Embeddings

​Image Generation

​Speech Recognition

​Object Detection

​Token Classification

​Fill Mask

​Image Classification

​Zero-Shot Image Classification

​Text Classification

​HTTP / other languages