Mindee Vision Models

Compare both Mindee vision models we track, all of them open-weight.

2 models · 2 open-weight · Updated Jan 2024

About Mindee Vision Models

Every Mindee vision model in our catalog is open-weight. Both publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on GPL v3 and Apache 2.0 licenses. The newest additions are Surya (Jan 2024) and docTR (Feb 2021).

The Mindee models we list cover OCR (2 models). For OCR, start with Surya or docTR.

1 of the 2 open Mindee models carry a permissive license, so commercial use is straightforward; the other 1 ship under terms worth reading before you deploy.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Compare their licenses, sizes, prices, and release dates in the tables below, then open any model page for the full specification.

Which Mindee Model Should You Use?

What each of the 2 Mindee vision models in our catalog is built for, and how you run it.

Surya: Best for: OCR. Open weights: GPL v3 license. Self-host it or run it here.
docTR: Best for: OCR. Open weights: Apache 2.0 license. Self-host it or run it here.

Open-Source Mindee Models

2 models with downloadable weights you can self-host under their licenses (GPL v3 and Apache 2.0).

Surya

Surya is an OCR and document layout analysis toolkit developed by Vikram Paruchuri and distributed via Mindee, first released in January 2024 under the GPL-3.0 license. It supports text recognition across more than 90 languages, document layout detection, reading order prediction, table recognition, and equation detection, providing a comprehensive set of tools for extracting structured information from document images.Surya is designed to operate without cloud API dependencies, running fully on local hardware with support for CPU and GPU inference. It is commonly used for digitizing scanned documents, extracting text from PDFs with complex layouts, and building automated document processing pipelines.

docTR

docTR (Document Text Recognition) is an open-source OCR toolkit developed by Mindee, with its initial public release in March 2021 under the Apache 2.0 license. It provides end-to-end document text recognition through a two-stage pipeline consisting of text detection and text recognition, both implemented as deep learning models. docTR supports multiple detection architectures including DBNet and LinkNet, and recognition architectures including CRNN and SAR, with both TensorFlow and PyTorch backends available.docTR is designed for reading text in document images including scanned PDFs, photographs of printed documents, and forms. It handles multilingual text recognition across standard Latin-script languages and is deployable through Roboflow Inference. It is suited for document digitization pipelines, automated form processing, and applications requiring accurate structured text extraction from document images.

Frequently Asked Questions About Mindee Vision Models

Which Mindee models can do OCR?

2 of the 2 Mindee vision models we track handle OCR: Surya and docTR. Each model page lists its full task coverage, license, and specs.

Are Mindee vision models open source?

Yes. Both Mindee vision models we track publish downloadable weights you can self-host under their licenses (GPL v3 and Apache 2.0).

What is the best Mindee model for OCR?

We do not publish a Mindee-only ranking, so pick on constraints rather than a label. 2 Mindee models handle OCR; the most recent is Surya (Jan 2024). Measured scores across every lab we test are on our OCR benchmark, linked at the bottom of this page. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model.

How many Mindee vision models are on Roboflow Playground?

We track 2 live Mindee vision models. The most recent addition is Surya, released Jan 2024.

This page lists both Mindee vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover OCR, among other tasks. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.