The MiniMax-M2.5 NIM Container is a deployable inference container for serving MiniMax-M2.5, a third-party text generation model optimized for complex agentic tasks including software engineering, tool use, search.
MiniMax-M2.5 NIM Container Overview
Description
The MiniMax-M2.5 NIM Container is a deployable inference container for serving MiniMax-M2.5, a third-party text generation model optimized for complex agentic tasks including software engineering, tool use, search, and office-work style workflows. The container provides an OpenAI-compatible API for self-hosted deployment, powered by the SGLang backend with FP8 quantization across supported NVIDIA GPU platforms.
The container components are ready for commercial use.
Third-Party Community Consideration
The model embedded in the container is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA MiniMax-M2.5 Model Card.
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for NVIDIA AI Products.
Use of this model is governed by the NVIDIA Open Model License. ADDITIONAL INFORMATION: Modified MIT License. MiniMax M2.5.
Deployment Geography:
Global
Release Date:
NGC 02/26/2026
Program Classes:
The MiniMax-M2.5 NIM Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| MiniMax-M2.5 | Text generation and agentic workflows (coding, tool use, search, office productivity) | Automatic (embedded in container) |
Deployment Details
The MiniMax-M2.5 NIM Container exposes an OpenAI-compatible chat completions API for seamless integration into existing applications and workflows.
API Endpoints:
/v1/chat/completions— Chat completions (streaming and non-streaming)/v1/models— List available models/health/ready— Health check
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Supported Hardware:
- NVIDIA Blackwell (B200, GB200, GB300, GB10, DGX Spark (two-node)
- NVIDIA Hopper (H100, H200, H20, H20-3e)
Runtime Engine: SGLang (via NVIDIA NIM) Precision: FP8
Operating System: Linux
Reference(s):
Container Version(s):
- 1.7.1-variant
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 we have 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 these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
NVIDIA Developer Community Forum
Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)