Yandex Vision OCR
aistudio.yandex.ru
What it is
Yandex Vision OCR recognizes printed and handwritten text in images and PDF files. Its models cover general page text, multi-column layouts, handwriting, tables, Markdown text, and mathematical formulas. Document-template models can recognize passports, driver licenses, vehicle registration certificates, and license plates, and return template fields. The service is accessed through gRPC or REST APIs. Results arrive as JSON Lines and can include recognized text and language, page, block, line, word, and image positions, plus layout types such as titles, headers, footnotes, and lists. Supported formats are JPEG, PNG, and PDF. The API accepts files up to 10 MB and images up to 20 megapixels; asynchronous PDF requests can cover up to 200 pages. Results remain on the server for three days. Each successful image or PDF-page recognition counts as one billed unit, while server errors and incorrectly configured requests are not charged. Listed rates range from free for printed text and license plate recognition to $0.01, paid once for several document, handwriting, and table models, billed per unit without VAT. There is no free plan.
Spec sheet
- What it does
- Vision OCR recognizes printed and handwritten text in images and PDF files, including text arranged in columns, tables, mathematical formulas, or document templates.Read 8 Oct 2026 · aistudio.yandex.ru
- Integrations
- A Yandex Cloud tutorial shows an image and PDF workflow using Object Storage, Cloud Functions, and Serverless Containers with Vision OCR.Read 8 Oct 2026 · yandex.cloud
- Support
- Yandex Cloud documentation says users can request information about resource operations from cloud logs by contacting support.Read 8 Oct 2026 · yandex.cloud
- Access control
- The ai.vision.user role allows users to analyze images with Vision OCR and view relevant cloud, folder, and quota information.Read 8 Oct 2026 · yandex.cloud
- API access
- The service is accessible through gRPC and REST APIs.Read 8 Oct 2026 · aistudio.yandex.ru
- Cloud responsibility
- Yandex Cloud describes security as shared responsibility, with responsibility depending on the service model and security tools and policies in use.Read 8 Oct 2026 · yandex.cloud
- Document extraction
- Document template models can recognize passports, driver licenses, vehicle registration certificates, and license plates and return template fields.Read 8 Oct 2026 · aistudio.yandex.ru
- Failed requests
- Only successful analysis attempts are chargeable; server errors and incorrectly configured requests are not charged.Read 8 Oct 2026 · aistudio.yandex.ru
- File formats
- Supported file formats are JPEG, PNG, and PDF.Read 8 Oct 2026 · aistudio.yandex.ru
- Input limits
- The maximum file size is 10 MB and the image size must not exceed 20 megapixels.Read 8 Oct 2026 · aistudio.yandex.ru
- Intended customers
- Yandex Cloud says its platform services are for large companies, medium-sized businesses, and private developers.Read 8 Oct 2026 · yandex.cloud
- Interfaces
- Vision OCR is accessible through gRPC and REST APIs.Read 8 Oct 2026 · aistudio.yandex.ru
- Languages
- The service uses one language model per recognition operation, so text in multiple languages may require separate requests.Read 8 Oct 2026 · aistudio.yandex.ru
- Layout
- The service groups words into lines, lines into blocks, and blocks into pages, and identifies block types such as headers, footnotes, titles, and lists.Read 8 Oct 2026 · aistudio.yandex.ru
- Maker launch
- Yandex Cloud says it launched in 2018.Read 8 Oct 2026 · yandex.cloud
- Output
- Recognition returns JSON Lines data with page, block, line, word, and image positions; words include text and recognition language.Read 8 Oct 2026 · aistudio.yandex.ru
- PDF limit
- Asynchronous OCR API requests support PDFs of up to 200 pages.Read 8 Oct 2026 · yandex.cloud
- Personal data
- Yandex Cloud says it implements personal data protection measures meeting first-level UZ-1 requirements under Russian Resolution No. 1119 and FSTEC Order No. 21.Read 8 Oct 2026 · yandex.cloud
- Pricing basis
- Each successful image recognition request is charged as one pricing unit, with each image or page of a multi-page PDF charged separately.Read 8 Oct 2026 · aistudio.yandex.ru
- Recognition models
- Models are available for general page text, multi-column text, handwriting, tables, Markdown text, and math formulas.Read 8 Oct 2026 · aistudio.yandex.ru
- Recognition output
- Recognition results include text and page, block, line, and word positions, and can include image positions and layout types.Read 8 Oct 2026 · aistudio.yandex.ru
- Request quotas
- The documented quotas are 1 synchronous request per second and 10 asynchronous requests per second.Read 8 Oct 2026 · yandex.cloud
- Result retention
- Recognition results are retained on the server for three days.Read 8 Oct 2026 · yandex.cloud
- Security compliance
- Yandex Cloud states that its information security management system is certified to ISO/IEC 27001, 27017, 27018, and 42001:2023.Read 8 Oct 2026 · yandex.cloud
- Supported files
- The documented supported file formats are JPEG, PNG, and PDF.Read 8 Oct 2026 · aistudio.yandex.ru
Plans and prices
License plate recognition Free per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Printed text recognition Free per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Document recognition (driving license) $0.01, paid once per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Document recognition (passport) $0.01, paid once per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Document recognition (vehicle registration certificate) $0.01, paid once per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Handwriting recognition $0.01, paid once per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Table recognition $0.01, paid once per unit, without VAT Each image or PDF page is charged separately · only successful requests are charged Read 8 Oct 2026 · aistudio.yandex.ru
Strong points and limits
Strong points
- Provides gRPC and REST APIs.
- Recognizes handwriting, tables, and math formulas.
- Returns text positions and layout information.
- Async PDF requests support up to 200 pages.
- Failed server or misconfigured requests are not charged.
Limits
- No free plan.
- Each operation uses one language model.
- Results are retained for three days.
- Maximum API file size is 10 MB.
Who it suits
Vision OCR suits developers and businesses that need API-based text extraction from images or PDFs, including structured documents and tables. Its single-language-per-operation model should suit workloads that can make separate requests for different languages.
Verdict
Vision OCR covers varied text and document layouts through cloud APIs, with structured positional output. Confirm file limits, per-operation language handling, result retention, and per-unit charges for your workload.
Where Specifiction places it
- AI Image Recognition Software#11 of 378.3
- AI OCR Software#12 of 308.3
Alternatives to Yandex Vision OCRAll alternatives →
Roboflow From $39/mo · Free plan 8.9 Visit 
Face++ Free plan 8.8 Visit