Mistral OCR
Mistral AI's OCR model API (OCR 4.1) returning markdown with tables, images and block-level bounding boxes; EU-hosted.
Mistral processes documents in the EU by default. OCR costs $4 per 1,000 pages; structured extraction to a schema costs $5 per 1,000 annotated pages. The model page does not confirm a batch discount for OCR, so use list rates when budgeting a backfill. Compare extraction results on your own documents.
- Headquarters
- 馃嚝馃嚪 France
- Parent jurisdiction
- 馃嚝馃嚪 France
- EU self-serve plan
- Available; check eligible plans and regions
- GDPR DPA
- Yes
- Billing
- payg
- Open source
- No
- Website
- mistral.ai
- Source last checked
- 2026-10-06
- Pricing evidence
- Published rates
Pricing
Calculated from the listed vendor rates; exclusions still apply. How to read these estimates.
| 1k additional pages |
|---|
| $4 |
Allowances, plan limits & calculation details
Rates are shown at their recorded precision. A zero means no charge in this calculation; the vendor may charge for things we leave out. See the notes for usage assumptions and currency conversions.
- Base fee / month
- $0
- Included pages / month (thousands)
- 0
- 1k additional pages
- $4
OCR 4.1 (mistral-ocr-4-1): $4 per 1,000 pages; Document AI annotations (structured extraction to a schema) $5 per 1,000 annotated pages. Older OCR 2/4.0 are retired. Batch API pricing for OCR not confirmed on the model page. Mistral AI is headquartered in Paris and processes data in the EU by default; DPA available.
Managed alternatives
At 100K pages / month. Adjust usage and requirements.
Mistral OCR: $4,800/yr estimated.
- GPT-6 Luna (via OpenAI API): $719/yr estimated 路 $4,081/yr bill differenceEstimated ratesPage cost uses an assumed image-token multiplier plus 300 prompt and 800 output tokens. Confirm actual token usage.
- Mistral Small 3.2 (via Scaleway Generative APIs): $845/yr estimated 路 $3,955/yr bill differenceModeled ratesToken cost assumes a 1,000脳1,400 px page, a 300-token prompt and 800 output tokens. Extraction quality and retries vary.
- Qwen3-VL-235B (via DeepInfra): $1,244/yr estimated 路 $3,556/yr bill differenceModeled ratesToken cost assumes a 1,000脳1,400 px page, a 300-token prompt and 800 output tokens. Extraction quality and retries vary.
- Gemini 3.1 Flash-Lite (via Gemini API): $1,866/yr estimated 路 $2,934/yr bill differenceModeled ratesToken cost assumes a 1,000脳1,400 px page, a 300-token prompt and 800 output tokens. Extraction quality and retries vary.
- LlamaParse (LlamaIndex): $4,500/yr estimated 路 $300/yr bill differencePublished rates
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you鈥檇 need to replace.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Compare Mistral OCR
Found a wrong rate or plan restriction? Report a correction with a current source.