Gemini 2.5 Pro OCR online
Google's most capable Gemini 2.5 model. Reads images and long PDFs natively.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- google/gemini-2-5-pro
- Type
- Vision model
- Price
- 8 credits / page ($8.00 per 1,000 pages)
- Typical speed
- 2.5 s / page
- Inputs
- PDF, images
- Languages
- 100+ languages
- Max pages per request
- 100
- Output
- Markdown, JSON
- Supports
- TablesHandwritingMathMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-2-5-pro",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Gemini 2.5 Pro speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Gemini 2.5 Pro pricing
Gemini 2.5 Pro costs 8 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $8.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 6 pages with this model. See pricing for credit packs.
Similar models
1GPTGeneral vision model. Good at messy scans and following extraction instructions.
openai/gpt11 credits / page2GPT-4.1OpenAI model from April 2025 with image input and a 1M-token context window.openai/gpt-4-111 credits / page3GPT-4oOpenAI's omni model (May 2024) with text and image input.openai/gpt-4o11 credits / pageAll Gemini 2.5 Pro alternativesBest OCR models by use case
Compare Gemini 2.5 Pro
Gemini 2.5 Pro vs GPTGemini 2.5 Pro vs GPT-4.1Gemini 2.5 Pro vs GPT-4oGemini 2.5 Pro vs Llama 3.2 90B VisionGemini 2.5 Pro vs UnstructuredGemini 2.5 Pro vs Gemini 2.0 Flash