Mistral AIOCR 4.1

External Link

Mistral OCR 4.1 extracts text, paragraph bounding boxes, structural block labels, and block-level confidence scores.

Context
Unknown
Inputs
Image, Document
Outputs
Text
Released
Jul 16, 2026

Providers & Pricing

Estimate workload cost →

At a Glance

Model Facts

Identity

Status
active
Developer ID
mistral-ocr-4-1
Released
Jul 16, 2026
Version
OCR 4.1
License
Unknown

Capacity

Context
Unknown
Maximum output
Unknown
Total parameters
Unknown
Active parameters
Unknown
Knowledge cutoff
Not reported

Interface and Access

Inputs
Image, Document
Outputs
Text
API available
Yes
Open weights
No
Self-hostable
No
Reasoning
No
Vision
Yes
Tool calling
No
Capabilities
bounding-box-extraction, document-ai, ocr, structured-annotations

This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.

Version Lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesmistral-ocr-4-1, ocr-4.1

Explicit Unknowns

  • Maximum output
  • Architecture
  • Tokenizer
  • Knowledge cutoff

Primary Evidence

Sources and Observation Date

Comparable Peers

Related Model Comparisons

All comparisons →
APairBContext
vscross-developer peersimage, text

Questions

OCR 4.1 FAQs

What is OCR 4.1?+

Mistral OCR 4.1 extracts text, paragraph bounding boxes, structural block labels, and block-level confidence scores. It is developed by Mistral AI and its current sourced lifecycle status is active.

What inputs and outputs does OCR 4.1 support?+

OCR 4.1's current record lists Image and Document as input and Text as output.

Is OCR 4.1 available through an API?+

OCR 4.1 is marked as API-available. The directly sourced provider records currently include Mistral AI.

How much does OCR 4.1 cost through an API?+

No directly sourced token price is currently attached to OCR 4.1. Missing prices remain unknown rather than being inferred from another model or provider.

What capabilities and tasks does OCR 4.1 support?+

OCR 4.1's recorded capabilities are bounding-box-extraction, document-ai, ocr, and structured-annotations. Its supported tasks are document-ai and ocr.

Can OCR 4.1 be self-hosted?+

OCR 4.1 is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.

Does OCR 4.1 have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are mistral-ocr-4-1 and ocr-4.1.

Which models can OCR 4.1 be compared with?+

The current compatible peer set includes Command A Vision. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

How current is the Model Markets record for OCR 4.1?+

OCR 4.1 was last verified Aug 29, 2026 from Mistral AI's primary source, “OCR 4.1 | Mistral Docs.” The evidence is classified as official fact.

Send Feedback