OCRRouter

Pixtral vs InternVL3.5

Pick InternVL3.5 for any new self-hosted OCR or document question answering project, because it is actively offered in nine sizes under Apache-2.0. Pick Pixtral only if you already call pixtral-12b-2409 on the Mistral API and want to keep that integration running. Pixtral is marked deprecated by Mistral, so it is a poor base for new work.

Pixtralmistral/pixtralInternVL3.5opengvlab/internvl
TypeVision modelVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed3.0 s / page3.0 s / page
Best forQuestions about document imagesSelf-hosted document understanding
Inputsimagesimages
LanguagesMultilingualMultilingual
Max pages per request500500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxesNoNo
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 Pixtral if

  • You want a hosted API: Pixtral was offered as pixtral-12b-2409 at $0.15 per million input and output tokens at launch.
  • You need question answering over charts and documents, where Mistral reports 90.7 ANLS on DocVQA and 81.8 on ChartQA (CoT).
  • You already have an integration on the Mistral API and its 128K token context lets you send many images per request.

Choose InternVL3.5 if

  • You want to choose a size: there are nine, from 1B to 241B-A28B, so you can trade accuracy for cost.
  • You have modest GPU hardware: models up to 30B run on a single A100, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.
  • You are starting a new project and want a family that is not marked deprecated, under Apache-2.0 and built on Apache-2.0 Qwen3.

Key differences

PixtralInternVL3.5
How you run itMistral API (pixtral-12b-2409) or self-hosted open weightsSelf-host only, with Transformers, LMDeploy or vLLM
LicenceApache-2.0Apache-2.0
Price$0.15 per million input and output tokens at launch on the API; free to self-host, you pay for computeFree, self-hosted, you pay for compute
Model sizeOne model, 12.4B (12B decoder + 400M vision encoder)1B to 241B-A28B; the 8B variant is 8.5B
Published OCR-related scoresDocVQA 90.7 ANLS, ChartQA 81.8 (CoT), MMMU 52.5 (CoT), all from MistralModel card shows OCR scores only as chart images, not text values
HardwareNot publishedUp to 30B on one A100; 38B needs two A100s; 241B-A28B needs eight A100s
Known failureReported drops on handwriting, small fonts and non-Latin scripts; Q4 quantization degrades small text; one HN user said OCR is not always close to correctGeneral VLM with no bounding boxes or layout output by default, so no word coordinates

Sources

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 details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": "mistral/pixtral","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Pixtral alternativesInternVL3.5 alternativesBest OCR models in 2026