Pixtral vs MiniCPM-V 4.5
Pick MiniCPM-V 4.5 for new self-hosted OCR work, such as on-device or single-GPU document Q&A. Pixtral 12B is deprecated and no longer maintained by Mistral, so keep it only for existing Mistral API integrations. Neither model returns coordinates or layout output.
Pixtralmistral/pixtral | MiniCPM-V 4.5openbmb/minicpm-v | |
|---|---|---|
| Type | Vision model | Vision model |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 3.0 s / page | 2.5 s / page |
| Best for | Questions about document images | OCR on edge devices |
| Inputs | images | images |
| Languages | Multilingual | 30+ languages |
| Max pages per request | 500 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | ✓ Yes |
| 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.
Which to choose
Choose Pixtral if
- You already run on the Mistral API and want to keep the pixtral-12b-2409 integration, which launched at $0.15 per million input and output tokens.
- You need question answering over charts and documents, where Mistral reports DocVQA 90.7 ANLS and ChartQA 81.8 (CoT).
- You send many images in one request, since the 128K token context allows it.
Choose MiniCPM-V 4.5 if
- You are starting a new project and want a model that is still being developed, rather than one Mistral marks as deprecated.
- You need to run on-device or at the edge, with int4, GGUF and AWQ builds on llama.cpp (b6282) or vLLM (v0.10.2).
- You want an 8.7B model on a single GPU for local document Q&A, with OpenBMB claiming leading OCRBench results and state of the art PDF parsing on OmniDocBench.
Key differences
| Pixtral | MiniCPM-V 4.5 | |
|---|---|---|
| Status | Deprecated by Mistral, no longer maintained | Current OpenBMB release |
| How you run it | Mistral API (pixtral-12b-2409) or open weights | Self-host only, with llama.cpp, vLLM, Ollama or Transformers |
| Licence | Apache-2.0 | Apache-2.0 weights and code |
| Price | $0.15 per million input and output tokens at API launch; free to self-host plus compute | Free, self-hosted, plus compute |
| Size | 12.4B (12B decoder + 400M vision encoder) | 8.7B (Qwen3-8B + SigLIP2-400M) |
| Published benchmarks | DocVQA 90.7 ANLS, ChartQA 81.8, MMMU 52.5 (reported by Mistral) | Not published as text. The model card shows scores only as images, so they are hard to verify |
| Known OCR failures | Reported drops on handwriting, small fonts and non-Latin scripts. Q4 quantization degrades small text OCR | No bounding box or layout output. Ollama and SGLang support were still pending on the model card. No int4 VRAM figure published |
Sources
- Mistral announcement
- Mistral Sept 2024 pricing
- Third-party deployment guide
- Hugging Face model card
- GitHub repo
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 detailsMiniCPM-V 4.5
8B vision model from OpenBMB (August 2025) built to run on devices, with strong OCR and document parsing.
MiniCPM-V 4.5 detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "mistral/pixtral","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Pixtral vs DeepSeek-VL2Pixtral vs InternVL3.5InternVL3.5 vs MiniCPM-V 4.5RolmOCR vs MiniCPM-V 4.5OCRmyPDF vs MiniCPM-V 4.5Amazon Textract vs MiniCPM-V 4.5Donut vs PixtralAzure Document Intelligence vs Pixtral
Pixtral alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026