{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","owned_by":"stepfun","description":"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...","context_window":262144,"max_tokens":230400,"type":"language","tags":["reasoning","tool-use","vision"],"released":1779985069,"modalities":{"input":["text","image","video"],"output":["text"]},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"input":"0.0000002","output":"0.00000115","input_cache_read":"0.00000004"},"legal":[]}