OCR NIM for multimodal retrieval and text extraction from images.
Image OCR v2 NIM Overview
Description
NVIDIA Nemotron OCR v2 NIM is an optical character recognition (OCR) microservice that extracts structured text from images for multimodal retrieval, document intelligence, and agentic workflows.
The container components are ready for commercial/non-commercial use.
License/Terms of Use
The NIM container is governed by the NVIDIA Software License Agreement (found at https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the Product-Specific Terms for NVIDIA AI Products (found at https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/).
Use of this model is governed by the NVIDIA Open Model License Agreement.
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography
Global
Release Date
Build.Nvidia.com on June 2026 via URL
NGC on 05/27/2026 via URL
Program Classes
The Image OCR v2 NIM container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| nemotron-ocr-v2 | Model extracts structured text from images | Automatic |
Deployment Details
NVIDIA AI models are designed and optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA GPU hardware and CUDA libraries, this NIM provides production-oriented OCR inference through standard NIM deployment workflows.
The OCR v2 container supports English and multilingual OCR runtime modes through the NIM configuration. Refer to the NIM release notes for the validated model modes, supported GPU profiles, and performance guidance for each release.
Reference(s)
N/A
Container Version(s)
See the NGC Tags tab for container versions.
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and has established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure the NIM is appropriate for the intended use case.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to industry-standard APIs. Visit the NIM Container page for release documentation, deployment guides, and more.
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.