> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepinfra.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepInfra Native API

> Advanced API with access to all model types including image generation, speech, object detection, and more.

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](/chat/overview) is simpler and recommended. Use the native API when you need model types beyond LLMs/embeddings, or when you need features like [webhooks](/account/webhooks) or [log probabilities](/chat/log-probs).

The base endpoint is:

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

## JavaScript client

```bash theme={null}
npm install deepinfra
```

## Text Generation (LLMs)

```javascript theme={null}
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);
```

```bash theme={null}
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

```javascript theme={null}
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]);
```

```bash theme={null}
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

```javascript theme={null}
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"));
}
```

```bash theme={null}
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

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

## Object Detection

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

## Token Classification

```bash theme={null}
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

```bash theme={null}
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

```bash theme={null}
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

```bash theme={null}
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

```bash theme={null}
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.