S
Step 3.7 Flash
StepFun's multimodal reasoning model with a 256K-token context for text, image, and video inputs.
Model Card
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...
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.