DeepSeek OCR

Name: DeepSeek OCR
Author: DeepSeek

by DeepSeek

Vision OCR

DeepSeek OCR is DeepSeek's document-understanding model, specialised for optical character recognition and extracting text from images and scans. It focuses on accurate, structured reading of visual documents.

Publisher: DeepSeek
API model name: deepseek-ocr
Context window: 8K tokens
Sizes: 3B
Licence: MIT

Run DeepSeek OCR

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

response = client.chat.completions.create(
    model="deepseek-ocr",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Extract all the text from this image."},
                {"type": "image_url", "image_url": {"url": "https://example.com/receipt.png"}},
            ],
        }
    ],
)

print(response.choices[0].message.content)

import { Pendra } from "pendra";

const client = new Pendra({ apiKey: "pdr_sk_..." });

const response = await client.chat.completions.create({
  model: "deepseek-ocr",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Extract all the text from this image." },
        { type: "image_url", image_url: { url: "https://example.com/receipt.png" } },
      ],
    },
  ],
});

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

Run DeepSeek OCR on your own UK infrastructure

Deploy a worker, install DeepSeek OCR, and start serving it through one sovereign API endpoint.

Get started free Read the quickstart

Related models

DeepSeek V4 Flash

DeepSeek

DeepSeek R1 Distill

DeepSeek