Skip to main content

Early access · OpenRouter-powered inference

The unified interface for document models.

Send an image or document once. Compare OCR-capable models, route by quality, speed, or cost, and receive one predictable response shape.

Get an API key Explore models
Vision models
200+
Model providers
30+
Platform fee
5%
Request format
1
request.shPOST /v1/ocr
curl https://api.docsrouter.com/v1/ocr \
  -H "Authorization: Bearer $DOCSROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/invoice.pdf",
    "strategy": "balanced",
    "options": { "output_format": "json" }
  }'
Objective routing

Pick the result you care about, or pass an exact OpenRouter model ID.

QualityGemini 2.5 Pro
SpeedGemini 2.5 Flash
CostGPT-4o Mini

One integration

Test the model, not your plumbing.

Keep one endpoint while you evaluate OCR accuracy, latency, and cost across the changing vision-model landscape.

  1. 01

    Send the source

    Upload an image or document, or pass a reachable file URL.

  2. 02

    Choose the route

    Select a named model or use a transparent quality, speed, cost, or balanced strategy.

  3. 03

    Use the result

    Receive extracted text, page output, structured fields, and usage metadata in one schema.

Start with real documents

Find the model that works for your OCR workload.

  • No subscription
  • Live model pricing
  • OpenAI-compatible API
Read the quickstartCreate account