StepFun Step 3.7 Flash

Step 3.7 Flash is a multimodal sparse Mixture-of-Experts (MoE) model designed for high-throughput reasoning, coding, and agentic workflows with native image understanding. It features 198B total parameters with approximately 11B activated per token, using a 45-layer transformer with 4,096 hidden size, 64 attention heads, and 288 experts activating 8 per token. The model combines a hybrid sliding-window and full-attention architecture with a dedicated vision encoder and Multi-Token Prediction, supporting up to a 256K context window for efficient long-context multimodal inference.