Mistral Medium 3 OCR online
Mistral's multimodal model from May 2025 with image input.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- mistral/mistral-medium-3
- Type
- Vision model
- Price
- 4 credits / page ($4.00 per 1,000 pages)
- Typical speed
- 2.5 s / page
- Inputs
- images
- Languages
- Multilingual
- Max pages per request
- 50
- Output
- Markdown, JSON
- Supports
- TablesMathMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral/mistral-medium-3",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Mistral Medium 3 speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Mistral Medium 3 pricing
Mistral Medium 3 costs 4 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $4.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 12 pages with this model. See pricing for credit packs.
Similar models
1Command A VisionCohere's enterprise vision model (July 2025) for documents, charts and scans.
cohere/command-a-vision4 credits / page2GPT-4.1 miniSmaller GPT-4.1 model with image input at a lower price.openai/gpt-4-1-mini3 credits / page3GPT-4o miniSmall, low-cost GPT-4o model with image input.openai/gpt-4o-mini3 credits / pageAll Mistral Medium 3 alternativesBest OCR models by use case
Compare Mistral Medium 3
Mistral Medium 3 vs Command A VisionMistral Medium 3 vs GPT-4.1 miniMistral Medium 3 vs GPT-4o miniMistral Medium 3 vs Google Cloud Vision OCRMistral Medium 3 vs DoclingMistral Medium 3 vs ABBYY FineReader