Mistral OCR is Mistral AI's image to text model, available from 3 providers, starting at $2.00 / 1M input and $3.00 / 1M output. An OCR model from Mistral designed to extract and interpret text from documents and images with high accuracy.
Specifications
Canonical IDmistral-ocr
TypeImage to Text
StatusActive
CreatorMistral AIMistral AI
Providers
Input ModalitiesPDF
Output ModalitiesText

Capabilities

Input1/5
Text·
Image·
Audio·
Video·
PDF
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Page In
$ / page
Input
$ / 1M
Output
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
mistral:ocr
N/AN/A$0.0020
Google Vertex AI logo
Google Vertex AI
vertex_ai/mistral-ocr-2505
N/AN/A$0.000500
Mistral AI logo
Mistral AI
mistral-ocr
$2.00$3.00$0.0010$1.00$1.50

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Mistral OCR 4Available
Mistral OCR 4 AnnotAvailable
DeepSeek-OCR 2Available
Qianfan OCR Fast66KDeprecated
Mistral OCR$2.00$3.00Current
DeepSeek-OCRAvailable
Document OCRAvailable
OCRAvailable
Prebuilt DocumentAvailable
Prebuilt LayoutAvailable
Prebuilt ReadAvailable

Model IDs

mistral-ocr
mistral-ocr-2505
mistral-ocr-2512
mistral-ocr-latest
mistral/mistral-ocr-2505-completion
mistral/mistral-ocr-latest
publishers/google/models/mistral-ocr-2505
vertex_ai/mistral-ocr-2505