Pixtralmistral/pixtral | GLM-4.1V-Thinkingzai/glm-4-1v-thinking | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Questions about document images | Small reasoning vision model |
| Inputs | images | images |
| Languages | Multilingual | Mainly English and Chinese |
| Max pages per request | 500 | 50 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
Pixtral
Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.
Pixtral detailsGLM-4.1V-Thinking
9B vision model from Z.ai with step-by-step reasoning (July 2025).
GLM-4.1V-Thinking detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
Use one, fall back to the other
{"model": "mistral/pixtral","fallbacks": ["zai/glm-4-1v-thinking"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Pixtral vs Doubao-Seed-1.6Pixtral vs GLM-4.5VInternVL3.5 vs GLM-4.1V-ThinkingRolmOCR vs GLM-4.1V-ThinkingFlorence-2 vs PixtralQwen-VL vs PixtralPixtral vs ChunkrClaude vs Pixtral
Pixtral alternativesGLM-4.1V-Thinking alternativesBest OCR models in 2026