PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- microsoft/phi-3-5-vision
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- images
- Languages
- English for vision
- Max pages per request
- 50
- Output
- Markdown, JSON
- License
- MIT
- Supports
- Multilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/phi-3-5-vision",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Phi-3.5-vision speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Phi-3.5-vision pricing
Phi-3.5-vision costs 1 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $1.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 50 pages with this model. See pricing for credit packs.
Similar models
1Llama 3.2 11B VisionMeta's smaller Llama 3.2 vision model (September 2024).
meta/llama-3-2-11b-vision1 credit / page2Mistral Small 3.2Open-weight 24B Mistral model with image input.mistral/mistral-small-3-21 credit / page3Kimi-VL-A3BMoonshot's mixture-of-experts vision model with about 3B active parameters (April 2025).moonshot/kimi-vl1 credit / pageAll Phi-3.5-vision alternativesBest OCR models by use case
Compare Phi-3.5-vision
Phi-3.5-vision vs Llama 3.2 11B VisionPhi-3.5-vision vs Mistral Small 3.2Phi-3.5-vision vs Kimi-VL-A3BPhi-3.5-vision vs ABBYY FineReaderPhi-3.5-vision vs DonutPhi-3.5-vision vs dots.ocr