A sparse MoE multimodal reasoning model good for enterprise, agentic and coding tasks.
Step-3.7-Flash is a StepFun vision-language model built on Step 3.5 Flash with additional vision capability for native multimodal, agentic, and coding-related use cases. The model is intended to process text and image inputs and produce text outputs, with emphasis on image understanding, fast throughput, and tool-use workflows.
This model is ready for commercial/non-commercial use.
This model 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-3.7-Flash Model Card.
GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and use of this model is governed by the NVIDIA Open Model Agreement. Additional Information: Apache 2.0 License.
Global
Use Case: Step-3.7-Flash is intended for multimodal understanding, agentic workflow support, coding and frontend-generation workflows, tool calling, and GUI-oriented tasks that use text, screenshots, or images as input.
Key Features:
Build.NVIDIA.com: 05/28/2026 via link
Huggingface: 05/28/2026 via link
Architecture Type: Transformer
Network Architecture: Mixture-of-Experts
Total Parameters: 198B
Active Parameters: Approximately 11B per token
Text backbone based on Step 3.5 Flash
Input Types: Text, Image
Input Formats: String, Red, Green, Blue (RGB)
Input Parameters: One-Dimensional (1D), Two-Dimensional (2D)
Other Input Properties: The vision module uses an image size of 728x728 pixels.
Input Context Length (ISL): 256k
Output Types: Text
Output Format: String
Output Parameters: One-Dimensional (1D)
Other Output Properties: None
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.
Runtime Engines:
Supported Hardware:
Preferred Operating Systems: Linux
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
Step-3.7-Flash v1.0
Data Modality: Text, Image
Image Training Data Size: Undisclosed
Text Training Data Size: Undisclosed
Training Data Collection: Undisclosed
Training Labeling: Undisclosed
Training Properties: Undisclosed
Testing Data Collection: Undisclosed
Testing Labeling: Undisclosed
Testing Properties: Undisclosed
Evaluation Benchmark Score: Undisclosed
Evaluation Data Collection: Undisclosed
Evaluation Labeling: Undisclosed
Evaluation Properties: Undisclosed
Acceleration Engine: vLLM
Test Hardware: NVIDIA 4xH100
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. 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 make sure you have proper rights and permissions for all input image content; if image includes people, personal health information, or intellectual property, the image generated will not blur or maintain proportions of image subjects included.
Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.