Mistral OCR 4.1
Mistral OCR 4.1 is a proprietary vision model from Mistral designed for optical character recognition. It excels at extracting structured text and layout information from images, providing outputs like bounding boxes, block types, and confidence scores.
Input
Output
Context
16K
Max Output
-
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Resources & Links
More models by Mistral
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Mistral OCR 4.1
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Mistral OCR 4.1 advertises a context window of 16,384 tokens. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
No. Mistral OCR 4.1 is a proprietary model (license: Proprietary): its weights are not distributed, and it runs only through Mistral's own API or a provider licensed to serve it.
Mistral OCR 4.1 accepts Text and Image and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Mistral OCR 4.1 is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Mistral OCR 4.1 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
Mistral OCR 4.1 cannot be self-hosted: its weights are not distributed. It is used through an API, either Mistral's own or the Inferbase gateway where it is served.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 23, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.