OCRRouter

Qwen-VL vs Pixtral

Pick Qwen-VL for mixed OCR plus reasoning, photos and screenshots with text, and new projects, because it is actively developed and reads 32 languages. Pixtral 12B suits question answering over charts and documents, or teams already on the Mistral API. Mistral marks it deprecated, so avoid it for new OCR work.

Qwen-VLqwen/qwen-vlPixtralmistral/pixtral
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page3.0 s / page
Best forFlexible extraction with promptsQuestions about document images
InputsPDF, imagesimages
Languages30+ languagesMultilingual
Max pages per request200500
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Qwen-VL if

  • It does OCR in 32 languages, while Pixtral is reported to lose accuracy on non-Latin scripts.
  • It comes in sizes from 2B to 235B-A22B MoE, all Apache-2.0, so you can match the model to your hardware.
  • It outputs layout positions, bounding boxes and a Qwen HTML document format, not just plain text.

Choose Pixtral if

  • It scores 90.7 ANLS on DocVQA per Mistral, which suits question answering over documents.
  • It has a 128K token context, so one request can carry many images.
  • It was priced at $0.15 per million input and output tokens on the Mistral API, and existing Mistral integrations keep working.

Key differences

Qwen-VLPixtral
LicenceApache-2.0Apache-2.0
Model sizes2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoEOne size: 12.4B (12B decoder + 400M vision encoder)
How you run itSelf-host open weights, or Alibaba Cloud hosted API. FP8 checkpoints need an H100-class GPU and CUDA 12+.Self-host open weights, or the Mistral API as pixtral-12b-2409
PriceFree to self-host. Hosted pricing on Alibaba Cloud: Not published.$0.15 per million input and output tokens at launch on the Mistral API. Free to self-host.
Output formatsPlain text, HTML, bounding boxes, JSON, MarkdownPlain text, Markdown, JSON
Benchmark64.6 on olmOCR-bench (Qwen 3 VL 8B), run by an independent party, below dedicated OCR models90.7 ANLS on DocVQA, 81.8 on ChartQA, 52.5 on MMMU, all reported by Mistral
Known failureCan loop and repeat the same text, mostly on low-quality scans and worse with greedy decoding. Qwen2.5-VL-32B GGUF often loops on scanned documents.Weaker on handwriting, small fonts and non-Latin scripts. Q4 quantization degrades small text OCR. Deprecated and no longer maintained.

Sources

What each one is

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL details

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 details

Try 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": "qwen/qwen-vl","fallbacks": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qwen-VL alternativesPixtral alternativesBest OCR models in 2026