Vision Models

Access 100+ vision-capable models through one unified API. All models support image input for OCR and document processing.

Models are updated on a regular basis. • Last updated: 12/17/2025

Loading models from OpenRouter...

Use Any Model via API

All these vision models are available through our OpenAI-compatible API. Just specify the model ID in your request.

curl -X POST https://api.docsrouter.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-001",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Extract text from this image"},
        {"type": "image_url", "image_url": {"url": "https://..."}}
      ]
    }]
  }'

View API Documentation