DeepSeek OCR 2

DeepSeek

deepseek/deepseek-ocr-2Open Weights

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

Benchmark Pricing$0.03 / 1M in$0.03 / 1M out

Context: 8,192 tokens•Max Output: 8,192 tokens•Released: 2026-01-27

TECHNICAL SPECIFICATIONS

Context Window8,1928.2K tokens

Max Output8,1928.2K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVision

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ DeepSeek OCR 2 does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 8,192 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling DeepSeek OCR 2 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DEEPSEEK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek/deepseek-ocr-2",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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