Skip to content
MistralOCRmistral-ocr-latest

Mistral OCR

Mistral OCR for OCR.

Explore Mistral OCR for OCR through the unified API. Supported interfaces and current availability are shown below.

  • OCR

Model details

Context window
—
Max output
—
Input
Documents, images
Output
Extracted text
Capabilities
Vision
Interfaces
OCR

Pricing

Prices use the units shown below. No gateway fees. Usage, size and model options may affect the total.

Mistral OCR pricing.
MetricPrice
/ page$0.004

Why teams pick it

  • Mistral OCR for OCR.

Call Mistral OCR

Mistral OCR answers on the API below — pick the one your code already speaks and just swap in your Inferray key.

/v1/ocrOCR · HTTP
curl https://api.inferray.com/v1/ocr \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral-ocr-latest",
  "document": {
    "type": "document_url",
    "document_url": "https://example.com/document.pdf"
  }
}'

More from Mistral

Questions about this model

Is there a free tier for Mistral OCR?
No. You add credit and pay Mistral OCR's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
Am I charged for failed requests?
No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
Is Mistral OCR included in Token Plans?
No. Mistral OCR is pay-as-you-go only; Token Plans cover the other text models in the catalog.
Does Mistral OCR support tool calling and vision?
Mistral OCR supports image input on Inferray. It does not support tool calling.
Is it the real Mistral OCR?
Yes. A request for mistral-ocr-latest is answered by Mistral OCR from Mistral, billed at its published list price. Inferray never substitutes a different or smaller model.