DeepSeek-OCR 2

Description

DeepSeek-OCR 2 is DeepSeek's open-weight 3B vision-language OCR model. Its DeepEncoder V2 encoder reorders visual tokens (visual causal flow) rather than raster-scanning, converting documents, screenshots, receipts and scene text into text or layout-aware Markdown, including tables, formulas and reading order.

Providers

Regolo

View provider details and policies.

Quantization: FP16

Capabilities

EU-Compliant API Access

Use DeepSeek-OCR 2 with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.pro/api/v1/chat/completions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ocr-2",
    "messages": [{"role": "user", "content": "Hello"}]
  }'