NVIDIA
NVIDIA
cuOpt
Container
NVIDIA
NVIDIA
cuOpt

NVIDIA® cuOpt™ is an open-source, GPU-accelerated engine for decision optimization designed to tackle large-scale problems with millions of variables and constraints.

Join or Subscribe to get accessSubscribe to the product below to access this premium content:
NVIDIA Developer Program
NVIDIA Developer ProgramJoin the Developer Program for access to free tools, support, and tech resources.
Get Access
NVIDIA AI Enterprise
NVIDIA AI EnterpriseAccelerate your AI agent development
Subscribe Now
Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.
Already Subscribed?Log in

What is NVIDIA cuOpt?

NVIDIA® cuOpt™ is an open-source, GPU-accelerated engine for decision optimization. It operates as a microservice in the cloud, utilizing the provided container. The cuOpt microservice leverages OpenAPI standards, serving endpoints running on port 5000 (by default) to accept optimization input data and return optimized routing solutions. For more details, please refer to the documentation shared below.

  • C API support ( Not supported under NVAIE)
    • Linear Programming (LP) - C
    • Quadratic Programming (MILP) - C
    • Mixed Integer Linear Programming (MILP) - C
  • C++ API support (Not supported under NVAIE)
    • cuOpt is written in C++ and includes a native C++ API. However, we do not provide documentation for the C++ API at this time. We anticipate that the C++ API will change significantly in the future. Use it at your own risk.
  • Python support
    • Routing (TSP, VRP, and PDP) - Python (Supported)
    • Linear Programming (LP), Quadratic Programming (QP) and Mixed Integer Linear Programming (MILP) - Python (Not supported under NVAIE)
  • Server support
    • Linear Programming (LP) - Server (Not supported under NVAIE)
    • Mixed Integer Linear Programming (MILP) - Server (Not supported under NVAIE)
    • Routing (TSP, VRP, and PDP) - Server (Supported)
  • gRPC remote execution (Beta) (Not supported under NVAIE)
    • Linear Programming (LP) / Quadratic Programming (QP) and Mixed Integer Linear Programming (MILP) - gRPC remote

Note : "Not supported under NVAIE" means these are beta versions and just add-ons, and doesn't come under NVAIE support.

Getting started with NVIDIA cuOpt

Learn more and get started with NVIDIA cuOpt. You can also explore the cuopt through the NVIDIA NGC catalog and NVIDIA LaunchPad. And discover how cuOpt can help your organization save time and money. You can also take the NVIDIA Deep Learning Institute Training, Learn How to Use Our Route Optimization Microservice to Drive Efficiency and Cost Savings.

Please visit the NVIDIA cuOpt Quickstart Guide on how to get started with cuOpt and details how to use container:

Security Vulnerabilities in Open Source Packages

Please review the Security Scanning tab to view the latest security scan results.

There are no Critical or High security vulnerabilities at the time of the release.

Get Help

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

NVIDIA AI Enterprise Documentation

Visit the NVIDIA AI Enterprise Documentation Hub for release documentation, deployment guides and more.

NVIDIA Licensing Portal

Go to the NVIDIA Licensing Portal to manage your software licenses. licensing portal for your products. Get Your Licenses

Additional resources and docs

License

GOVERNING TERMS: The container is governed by the NVIDIA Software License Agreement (found at https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) 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/).

Publisher
NVIDIA
NVIDIA
Latest Tag26.6.0-cuda12.9-py3.14
UpdatedJune 10, 2026 UTC
Compressed Size4.02 GB
Multinode SupportNo
Multi-Arch SupportYes

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.