--- title: "Free OCR and Document AI APIs in 2026: Google Document AI, Azure, AWS Textract, Mistral OCR, Tesseract" slug: "free-ocr-api" description: "Free OCR and document AI APIs checked on 2026-10-28: Google Document AI, Azure, AWS Textract, Mistral OCR, OCR.space, Tesseract. Pages per month and sources." published: "2026-10-28" updated: "2026-10-28" verifiedAt: "2026-10-28" canonical: "https://aifree.dev/learn/free-ocr-api" --- # Free OCR and Document AI APIs in 2026: Google Document AI, Azure, AWS Textract, Mistral OCR, Tesseract > Free OCR and document AI APIs checked on 2026-10-28: Google Document AI, Azure, AWS Textract, Mistral OCR, OCR.space, Tesseract. Pages per month and sources. - Time: 10 minutes: pick a service, get a key, send one scan - You need: An account with the provider; Google Cloud and AWS ask for a billing account (card) even for their free allowance; A PDF or image to read: sync calls differ in how many pages they take at once; For Tesseract, PaddleOCR or Docling: your own machine (open source, no key) - Last checked: 2026-10-28 OCR (optical character recognition) turns a scan or a photo of text into text you can search and copy. "Document AI" services go one step further: they also return tables, form fields and reading order. Free offers range from a few hundred pages a month to open-source engines you run yourself. Everything below was checked on each vendor's pricing or docs page on 2026-10-28. ## Free OCR and document AI quotas side by side | Service | What is free | Resets | Card | Main limits | Checked | | --- | --- | --- | --- | --- | --- | | [Google Document AI](https://cloud.google.com/document-ai/pricing) (Enterprise Document OCR) | First 1,000 pages at $0.00, then $1.50 per 1,000 | Billing cycle is monthly | Billing must be enabled on the project | Paid after 1,000 pages; other processors (Form Parser) are not free | 2026-10-28 | | [Google Cloud Vision](https://cloud.google.com/vision/pricing) (Document Text Detection) | First 1,000 units at $0.00, then $1.50 per 1,000 | Not stated on the page | Billing account | Images; one unit per image or PDF page | 2026-10-28 | | [Azure Document Intelligence](https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/) | Free (F0) tier: 0 to 500 pages free per month | Monthly | Azure account | Only the first 2 pages of each request, 4 MB per file, 1 request a second | 2026-10-28 | | [AWS Textract](https://aws.amazon.com/textract/pricing/) | 1,000 pages a month of plain text detection; 100 pages for tables, forms and layout | Monthly, for the first 3 months | AWS account | Synchronous calls take 1 page per PDF; 6 Latin-script languages | 2026-10-28 | | [Mistral OCR](https://mistral.ai/pricing) | No OCR-specific free allowance stated; the free Studio plan has rate-limited API access | n/a | No | Paid OCR is $2 per 1,000 pages ($1 in batch) | 2026-10-28 | | [OCR.space](https://ocr.space/ocrapi) | 25,000 requests a month, plus 1,000 for the newest engine | Monthly | No (free key) | 500 requests a day per IP, 1 MB file, 3 PDF pages, watermark on searchable PDFs | 2026-10-28 | | [LlamaParse](https://www.llamaindex.ai/pricing) | 10,000 credits a month | Monthly | Not stated | 1 credit a page (fast), 3 (cost-effective), 10 (agentic) | 2026-10-28 | | [Upstage Document Parse](https://www.upstage.ai/pricing) | Nothing on the public price list; free for universities, hospitals and nonprofits that apply | n/a | n/a | Standard $0.01 a page, Enhanced $0.03; OCR alone $0.0015 | 2026-10-28 | | [Tesseract](https://github.com/tesseract-ocr/tesseract) | Open source (Apache-2.0), 5.5.3 | n/a | No | 100+ languages; plain text only, no table structure | 2026-10-28 | | [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) | Open source (Apache-2.0), 3.7.0 | n/a | No | 100+ languages; models run on CPU or GPU | 2026-10-28 | | [Docling](https://github.com/docling-project/docling) | Open source (MIT), v2.143.1 | n/a | No | Converts PDFs and Office files to Markdown or JSON | 2026-10-28 | Source: each vendor's pricing page or docs, linked in the table and under Sources, checked 2026-10-28. ## Cloud quotas you can keep using - **Azure Document Intelligence** has the most generous page count among the big clouds: the F0 tier lists "0 - 500 pages free per month". The catch is in the docs: the free tier "limits analyze response to only the first two pages in a request", with 4 MB per file and one request a second, so it suits a test or a form of a few pages, not a 100-page report. - **Google Document AI** prices Enterprise Document OCR at $0.00 for the first 1,000 pages and $1.50 per 1,000 after that. Its setup page tells you to check that billing is enabled for the project, so the free pages sit behind a billing account. - **AWS Textract** gives 1,000 pages a month of plain text detection, but only for the first three months, and 100 pages a month if you ask for tables, forms or layout. A synchronous call reads one page of a PDF; longer files go through the asynchronous API. ## Free keys without a cloud account - **OCR.space** is the easiest to try: register for a free key and send an image or a PDF of up to 3 pages. The free plan allows 25,000 requests a month, but only 1 MB per file and 500 requests a day per IP address. - **LlamaParse** (LlamaCloud) gives 10,000 credits a month on the free plan. A page costs 1 credit in the fast tier, 3 in cost-effective and 10 in agentic, so the free allowance is about 10,000, 3,300 or 1,000 pages. It is aimed at feeding documents to an LLM. - **Mistral OCR** is cheap rather than free: $2 per 1,000 pages, $1 in batch mode, according to its launch post. We could not confirm an OCR allowance in Mistral's free plan, so test with a small file before you plan on it. See the [Mistral free plan](https://aifree.dev/offer/mistral-ai-free-plan). ## Self-hosted: Tesseract, PaddleOCR, Docling **Tesseract** is the classic open-source engine (Apache-2.0, 5.5.3 released 2026-07-24) with more than 100 languages. It returns text, not tables. **PaddleOCR** (Apache-2.0, 3.7.0 from 2026-06-11) handles many scripts and layouts, and can parse whole documents. **Docling** (MIT) converts PDFs and Office files to Markdown or JSON and can run OCR on scanned pages. All three cost only your machine, and the document never leaves it, which matters for contracts or medical records. ## Which one to pick - **A few hundred pages for a test:** Azure's 500 pages, or Google's first 1,000. - **Many small images, no cloud account:** OCR.space. - **Tables and forms for a pipeline:** Azure Layout, Textract tables (100 free pages a month) or LlamaParse. Check the result: scans of tables are where OCR fails most. Why is explained in [why chatbots mangle tables in a PDF](https://aifree.dev/explain/pdf-tables). - **Private documents or unlimited volume:** Tesseract, PaddleOCR or Docling on your own machine. - **Non-Latin scripts and handwriting:** AWS Textract reads handwriting in English only; try PaddleOCR or a cloud model on a sample first. ## Steps 1. Pick one scan of a few pages and note whether it has tables. 2. For no-account testing, get a free key at ocr.space and run: `curl -H "apikey: $OCR_SPACE_KEY" -F "file=@scan.png" -F "language=eng" https://api.ocr.space/parse/image` 3. For a local run, install Tesseract and run `tesseract scan.png out -l eng`; the text lands in out.txt. 4. For a cloud test, create the resource (Azure F0 or a Google Document AI processor), send the same scan and compare the text with the Tesseract output. 5. Check the usage counter in the console before you send a large batch. ## Limits and the catch - **Pages are counted differently.** Azure counts every page analysed; Textract bills tables and forms apart from plain text; LlamaParse bills credits, not pages. - **Free allowances can end.** Textract's free tier lasts three months; Google's and Azure's rules can change, so re-check the pricing page. - **Accuracy is not in the price list.** A low-resolution scan, skewed text or a table can come back garbled on any service; check a few numbers by hand. - **Your documents are sent to the vendor.** For contracts, ID cards or patient data read the vendor's data terms, or use a local engine. ## Offers in this guide - [Mistral AI Free Plan](https://aifree.dev/offer/mistral-ai-free-plan.md): Free tier, no card. Free Vibe agent and rate-limited Studio API access; no monthly API credits - [Upstage AI Initiative Free Access](https://aifree.dev/offer/upstage-ai-initiative-free-access.md): Student program, no card. Free Solar Pro 4 and Document Parse access for education and nonprofits ## Frequently asked questions ### Is there a free OCR API? Yes. On 2026-10-28 OCR.space gave 25,000 requests a month with a free key, Azure Document Intelligence 500 pages a month (first 2 pages per request), Google Document AI its first 1,000 pages, and AWS Textract 1,000 pages a month for three months. Tesseract, PaddleOCR and Docling are open source and free to run yourself. ### Is Google Document AI free? The first 1,000 pages of Enterprise Document OCR are priced at $0.00 and the next pages cost $1.50 per 1,000. Billing must be enabled on your Google Cloud project, and other processors such as Form Parser are charged from the first page. ### Is Mistral OCR free? Mistral OCR is priced per page: $2 per 1,000 pages, or $1 in batch mode, per its launch post. Its pricing page does not state an OCR-specific free allowance, so a free Studio account may be limited; test a small file first. ### What is the best free OCR for tables in a PDF? Azure Document Intelligence (Layout, within 500 free pages a month), AWS Textract (100 free table pages a month for three months) and LlamaParse (10,000 credits a month) return table structure. Tesseract returns text only. Check a few cells by hand either way. ### Can I run OCR for free on my own computer? Yes. Tesseract (Apache-2.0) reads 100+ languages, PaddleOCR (Apache-2.0) adds layout parsing, and Docling (MIT) converts PDFs to Markdown. They need no key and the document stays on your machine. ## Sources - https://cloud.google.com/document-ai/pricing - https://cloud.google.com/vision/pricing - https://docs.cloud.google.com/document-ai/docs/setup - https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/ - https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits?view=doc-intel-4.0.0 - https://aws.amazon.com/textract/pricing/ - https://docs.aws.amazon.com/textract/latest/dg/limits-document.html - https://mistral.ai/pricing - https://mistral.ai/news/mistral-ocr-3 - https://ocr.space/ocrapi - https://www.llamaindex.ai/pricing - https://developers.llamaindex.ai/python/cloud/general/pricing/ - https://www.upstage.ai/pricing - https://github.com/tesseract-ocr/tesseract - https://github.com/PaddlePaddle/PaddleOCR - https://github.com/docling-project/docling HTML page: https://aifree.dev/learn/free-ocr-api