Roboflow

AzureMicrosoftReleased Sep 2021MIT

TrOCR

TrOCR has no score on the current Vision Evals. On the earlier Vision Evals board (last updated July 9, 2026) it passed 26.2% of OCR tasks (#56 of 58).

It is an open-weight model from Microsoft under the MIT license, and free for commercial use.

TrOCR Vision Evals

TrOCR has not yet been evaluated on the current benchmark. The results below are from the legacy version of Vision Evals, our previous benchmark. See the current Vision Evals

HighestLowest
This model#56 of 5826.2% pass rate · better than 3%
Score26.2%pass rate across 229 tasks
Speed0.28savg response per task
Cost—pricing unavailable
Tokens—tokens unavailable
Score key:≥75%40–74%<40%
CategoryPassedScore
Text Recognition16 / 30
53.3%
Focused Scene OCR34 / 99
34.3%
License Plate Recognition10 / 30
33.3%
VQA & Extraction0 / 60
0%
Handwritten Math0 / 10
0%

Scores based on a single evaluation run · Methodology

View all legacy Vision Evals results →

TrOCR Overview

TrOCR (Transformer-based Optical Character Recognition) is an end-to-end OCR model released in September 2021 by Microsoft Research. It departs from the traditional two-stage OCR pipeline — which typically combines a CNN-based feature extractor with an RNN-based sequence decoder — by using a pure Transformer architecture composed of a pretrained image Transformer encoder and a pretrained text Transformer decoder, an approach that later became standardized as the VisionEncoderDecoder pattern in Hugging Face Transformers.

TrOCR License

MIT · Permissive license

TrOCR is released under MIT, a permissive license. The TrOCR license lets you use, modify, and sell work built on the model, with the copyright notice as the only real obligation and no requirement to open-source related code changes.

Commercial use
Permitted with no separate commercial license. No usage caps, revenue thresholds, or field-of-use limits apply to TrOCR.
Modification
Permitted. You can fine-tune or rewrite TrOCR and keep the result closed-source.
Redistribution
Permitted. Include the original copyright and permission notice in copies or substantial portions of the work.

MIT grants no explicit patent license and disclaims all warranties. If patent exposure is a concern for your deployment, review it with counsel before launch.

Read the full MIT license ↗

Do I need a commercial license for TrOCR?

No commercial license is needed for TrOCR: permissive terms let you keep related code private while deploying commercially.

Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

This model is released under the MIT License, a short and permissive open-source license that allows commercial use, modification, and redistribution.

Yes. Under the terms of the MIT license, you can freely use this model for commercial purposes. You must retain the copyright notice and license text when redistributing.

License information is provided as a guide and is not legal advice.

TrOCR Details

Details

Categoryopen
ModalityVision
Parameters61.4M-600M
LicenseMIT
Release DateSep 2021

Vision Tasks

OCR

Resources

Price vs. performance

Estimated cost per task vs. OCR score, for this model and others ranked near it. Upper-left is the sweet spot (high quality, low cost). Based on Vision Evals (legacy) results.

6 of 7 models plotted · 1 not yet evaluated

ModelScoreMedian tokensEst. cost / taskCompare
AnthropicClaude Sonnet 4.567.3%866$0.0039Compare
GoogleGemma 3 4B64.2%314<$0.0001Compare
OpenAIGPT-5.4 Nano62.5%294$0.0001Compare
AnthropicClaude Haiku 4.561.6%861$0.0012Compare
QwenQwen3.6 Plus58.5%166$0.0001Compare
AzureTrOCR(this model)26.2%———
MoonshotAIKimi K2.519.6%706$0.0007Compare

Alternatives to TrOCR

Other models worth comparing for similar use cases.

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.
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.
Google Vision OCR, released as part of the Cloud Vision API’s general availability in February 2016, is a proprietary Google Cloud service for extracting text from images and…
Gemini 2.5 Flash-Lite, released for general availability on July 22, 2025, is the most cost-efficient model in the Gemini 2.5 family, designed for high-volume and…
GPT-5 Nano, released by OpenAI on August 7, 2025, is the smallest and most cost-efficient model in the GPT-5 family.