POST
/
v1
/
chat
/
completions
DeepSeek OCR
curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "max_tokens": 123,
  "temperature": 123
}
'
Extract text from images using DeepSeek’s vision capabilities.

​
Overview

DeepSeek OCR allows you to extract text from images, documents, and screenshots. The model can recognize text in multiple languages and handle various document formats.

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
ID of the model to use. Use deepseek-chat with vision capabilities.
​
messages
array
required
A list of messages with image content for OCR processing.
​
max_tokens
integer
Maximum number of tokens to generate.
​
temperature
number
default:"0"
Sampling temperature. Lower values recommended for OCR accuracy.

​
Request Example

curl -X POST https://api.example.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Please extract all text from this image."},
          {"type": "image_url", "image_url": {"url": "https://example.com/document.png"}}
        ]
      }
    ],
    "temperature": 0,
    "max_tokens": 4096
  }'

​
Response Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is the extracted text from the image:\n\nINVOICE\nInvoice Number: INV-2024-001\nDate: January 15, 2024\n\nBill To:\nJohn Smith\n123 Main Street\nNew York, NY 10001\n\nItems:\n1. Product A - $50.00\n2. Product B - $75.00\n\nTotal: $125.00"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1150,
    "completion_tokens": 95,
    "total_tokens": 1245
  }
}

​
Supported Image Formats

  • PNG
  • JPEG
  • WebP
  • GIF

​
Use Cases

  • Document digitization
  • Receipt and invoice processing
  • Screenshot text extraction
  • Handwritten text recognition
  • Multi-language text extraction

​
Available Models

  • deepseek-chat