Phi-4-multimodal OCR online
Microsoft's 5.6B text, vision and audio model (February 2025). Scores 84.4 on OCRBench per its model card.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- microsoft/phi-4-multimodal
- Type
- Vision model
- Price
- 2 credits / page ($2.00 per 1,000 pages)
- Typical speed
- 2.5 s / page
- Inputs
- images
- Languages
- English for vision
- Max pages per request
- 500
- Output
- Markdown, JSON
- License
- MIT
- Supports
- TablesMath
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/phi-4-multimodal",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Phi-4-multimodal speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Phi-4-multimodal pricing
Phi-4-multimodal costs 2 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $2.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 25 pages with this model. See pricing for credit packs.
Similar models
1InternVL3.5Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.
opengvlab/internvl2 credits / page2Gemini 2.5 Flash-LiteLowest-cost Gemini 2.5 model, with image and PDF input.google/gemini-2-5-flash-lite1 credit / page3GPT-4.1 miniSmaller GPT-4.1 model with image input at a lower price.openai/gpt-4-1-mini3 credits / pageAll Phi-4-multimodal alternativesBest OCR models by use case
Compare Phi-4-multimodal
Phi-4-multimodal vs InternVL3.5Phi-4-multimodal vs Gemini 2.5 Flash-LitePhi-4-multimodal vs GPT-4.1 miniPhi-4-multimodal vs QVQ-72B-PreviewPhi-4-multimodal vs NougatPhi-4-multimodal vs GPT