Mistral OCR Models by MistralAI
MistralAIProprietary
1 model2025
Details
ResearcherMistralAI
LicenseProprietary
Commercial useCommercial use: conditional
Models1
Released2025
Capabilities
VisionAll models
MultimodalAll models
Links
WebsiteAbout
Mistral's document AI and optical character recognition model family, designed for extracting structured information from documents, PDFs, and images.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Mistral Document AI 2512Current
Use when the workload needs document ai and multimodal inputs.
2025-12document aimultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral Document AI 2512 | Use when the workload needs document ai and multimodal inputs. | 2025-12 | document aimultimodal inputs | Current |
Release Timeline
1 release group2025-12
1 current
Mistral Document AI 2512
Currentdocument aimultimodal inputs
Specifications(1 models)
| Model | Released | Vision | Multimodal |
|---|---|---|---|
| Mistral Document AI 2512 | 2025-12 | Yes | Yes |
Available From(1 provider)
Frequently Asked Questions
- What is Mistral OCR used for?
- Mistral OCR is used for document ai, vision and multimodal work, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mistral OCR compare to Ministral?
- Mistral OCR by MistralAI is strongest where you need document ai, while Ministral by MistralAI is the closest related family to check for vision and multimodal work. Mistral OCR has 1 listed variant, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which Mistral OCR model should I use?
- If price is the main constraint, use the pricing table first because Mistral OCR does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Mistral Document AI 2512 with multimodal inputs.
