# DeepSeek OCR

> Run DeepSeek OCR by infsh online or via API. Pay per run, no setup.

**URL:** https://inference.sh/apps/infsh/deepseek-ocr
**Last updated:** 2026-05-22

---

Extracts and converts text from documents, especially good at reading images, photos, handwriting, charts, and graphs.

- app: `infsh/deepseek-ocr`
- maker: [infsh](https://inference.sh/apps/infsh.md)
- category: [text](https://inference.sh/apps/category/text.md)
- tasks: [ocr](https://inference.sh/apps/tag/ocr.md)
- price: GPU time, billed per millisecond
- runs via: api, javascript and python sdk, belt cli, mcp

## deepseek-ocr API Guide

### About
extracts and converts text from documents, especially good at reading images, photos, handwriting, charts, and graphs.

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Setup Your API Key
Set `INFERENCE_API_KEY` as an environment variable. Get your key from settings → api keys.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

#### Run and Get Result

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


result = client.run({
        "app": "infsh/deepseek-ocr@5bh7zsyv",
        "input": {
            "image": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


## stream=True yields updates as they arrive
for update in client.run({
        "app": "infsh/deepseek-ocr@5bh7zsyv",
        "input": {
            "image": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

### 2. Authentication
The API uses API keys for authentication. See the authentication docs for detailed setup instructions.

### 3. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "infsh/deepseek-ocr@5bh7zsyv",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 4. Schema

#### Input
- **image** (string) *required*: Input image or PDF file to perform OCR on
- **task** (string): markdown: structured document conversion (best for papers, tables, math). ocr: general OCR with layout detection. text: plain text extraction. figure: parse charts and diagrams. describe: image description.
- **mode** (string): Model mode affecting image processing parameters. Gundam is optimized for general use.

#### Output
- **text** (string): The extracted text from the image

## other text apps

- [Archive Download](https://inference.sh/apps/archive/download.md): from $0.00000277/sec
- [Archive Metadata](https://inference.sh/apps/archive/metadata.md): from $0.00000277/sec
- [Archive Search](https://inference.sh/apps/archive/search.md): from $0.00000277/sec
- [Wayback Machine Availability Check](https://inference.sh/apps/archive/wayback.md): from $0.00000277/sec
- [Markdown to Word Converter](https://inference.sh/apps/infsh/markdown-to-word.md): from $0.00000277/sec

## faq

### how much does DeepSeek OCR cost?

GPU time, billed per millisecond. you pay per run from your inference shell credits. no subscription is required.

### how do I run DeepSeek OCR via api?

call infsh/deepseek-ocr with the javascript or python sdk, the rest api, or `belt app run infsh/deepseek-ocr` from a terminal. the api reference on this page lists every input.

### who makes DeepSeek OCR?

DeepSeek OCR is made by infsh and runs on inference shell. every infsh app is listed at https://inference.sh/apps/infsh.

### can my agent use DeepSeek OCR?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to DeepSeek OCR?

other text apps on inference shell include Archive Download, Archive Metadata, Archive Search, Wayback Machine Availability Check. they run through the same api, so switching is a one-line change.