Vidsembly turns PowerPoint decks, PDFs and documents into narrated videos with AI voiceover or your own voice clone in 12 languages, then lets you host and share them with a link or embed.
Mistral AI's OCR API that extracts text and structured content from PDFs and images, for developers building document pipelines. Mistral lists OCR 4.1 at $4 per 1,000 pages; no free-tier terms were stated on the pages read.
Mistral OCR is an OCR processor in Mistral AI's API that extracts text and structured content from PDFs and images. According to the documentation, it preserves document structure, formats tables, extracts headers and footers, and returns confidence scores. It is aimed at developers who call it through the API rather than use a desktop application.
The docs state that the mistral-ocr-latest alias points to the latest OCR model. The current model card is OCR 4.1 (API name mistral-ocr-4-1), listed as generally available on July 16, 2026. It offers paragraph-level bounding box extraction with structural block labels and block-level confidence scores, plus structured annotations and OCR through the /v1/ocr endpoint and batching through /v1/batch. Table formatting and header and footer extraction need OCR 2512 or newer, and block extraction needs OCR 4 or newer.
The model page lists OCR 4.1 at $4 per 1,000 pages and $5 per 1,000 annotated pages. Mistral's pricing page says OCR is priced per 1,000 pages and that batch processing reduces the price by 50%, without saying whether that applies to OCR. The pages read today state no OCR free-tier terms, usage limits, data residency commitments or compliance certifications.
The OCR 4.1 model page lists $4 per 1,000 pages and $5 per 1,000 annotated pages in USD.
The pages read today state no OCR free-tier terms or usage limits. Check Mistral's pricing page and account plans for current free access.
Website: https://docs.mistral.ai/capabilities/document_ai/basic_ocr/
Company: Mistral AI
Pay-per-page OCR API for PDFs and images, for developers. Biggest limit: no free-tier or limit terms were stated on pages read. OCR 4.1 is $4 per 1,000 pages.
| Pricing model | Usage-based |
|---|---|
| Free tier | Not verified |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | Not verified |
| Public API | Yes |
| Self-hostable | Not verified |
| Official site | Not verified |
| Can a general AI assistant replace it? | Compare Google Document AI or Amazon Textract for hosted APIs; olmOCR or Docling if you need to run models yourself. |
| Last verified | 2026-11-17 by editor |
Vidsembly turns PowerPoint decks, PDFs and documents into narrated videos with AI voiceover or your own voice clone in 12 languages, then lets you host and share them with a link or embed.
Microsoft Azure service that extracts text, key-value pairs and tables from printed and handwritten forms, PDFs and images, for developers. Microsoft says free and standard pricing options exist; limits are on a page not readable today.
Open-source OCR engine and command-line program that recognizes text in images, for developers building OCR into their own software. Free under the Apache License 2.0 and recognizes more than 100 languages out of the box.
Open-source toolkit that parses PDFs, Office files, images and other formats into structured output for generative AI pipelines, for developers. Free under the MIT license and can run locally, including air-gapped.
Numerous.ai brings ChatGPT into Google Sheets and Microsoft Excel through an =AI function you can use in any cell, with no API key needed. Its site does not publish plan prices, so check the add-on before you rely on it.
Shortcut is an AI agent for building and editing Excel workbooks, aimed at finance work. It runs on the web, as a desktop app and as Excel and Google Sheets plugins; the free tier includes 20 credits a week.
Need the outcome rather than the software?