Step 3.5 Flash is a sparse Mixture-of-Experts (MoE) large language model developed by StepFun, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency
Step 3.5 Flash NIM Container Overview
Description:
The Step 3.5 Flash NIM Container packages StepFun's Step 3.5 Flash sparse Mixture-of-Experts (MoE) large language model for optimized deployment using NVIDIA Inference Microservices (NIM). The container provides a production-ready inference endpoint with industry-standard API compatibility, enabling developers to deploy frontier reasoning and agentic AI capabilities with exceptional efficiency — 196.81B total parameters with only ~11B active per token for real-time responsiveness.
The container components are ready for commercial/non-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 Step 3.5 Flash 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: Apache 2.0
You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.
Deployment Geography:
Global
Release Date:
NGC Catalogue: 02/2026 via link
Program Classes:
The Step 3.5 Flash NIM Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Step 3.5 Flash | High-performance LLM for coding assistants, deep research agents, GUI automation, and complex multi-step reasoning tasks | Automatic |
Deployment Details:
The Step 3.5 Flash NIM Container exposes an OpenAI-compatible API endpoint for seamless integration. Deploy using standard container orchestration tools (Docker, Kubernetes) with NVIDIA GPU support.
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.
Reference(s):
Container Version(s):
Step 3.5 Flash NIM v1.0
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/)