Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Tokens processed for this model through Reroute, per day, over the last 30 days.
Daily token volume shows up here as soon as the first request for this model completes.