GLM-4.5V OCR online
Z.ai's open vision-language model (August 2025) built on GLM-4.5-Air.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- zai/glm-4-5v
- Type
- Open source
- Price
- 3 credits / page ($3.00 per 1,000 pages)
- Typical speed
- 2.5 s / page
- Inputs
- images
- Languages
- Mainly English and Chinese
- Max pages per request
- 50
- Output
- Markdown, JSON with positions
- License
- MIT
- Supports
- TablesHandwritingMathBounding boxesMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zai/glm-4-5v",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'GLM-4.5V speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
GLM-4.5V pricing
GLM-4.5V costs 3 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $3.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 16 pages with this model. See pricing for credit packs.
Similar models
1Qwen2.5-VL-72BLargest Qwen2.5-VL model (January 2025), strong on documents, charts and grounding.
qwen/qwen2-5-vl-72b3 credits / page2Qwen-VLAlibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.qwen/qwen-vl2 credits / page3Qwen3-VLAlibaba's Qwen3 vision-language family (2025), with expanded OCR language support.qwen/qwen3-vl2 credits / pageAll GLM-4.5V alternativesBest OCR models by use case
Compare GLM-4.5V
GLM-4.5V vs Qwen2.5-VL-72BGLM-4.5V vs Qwen-VLGLM-4.5V vs Qwen3-VLGLM-4.5V vs Florence-2GLM-4.5V vs OCRmyPDFGLM-4.5V vs dots.ocr