Back to all models
stepfun
stepfunStepFun: Step 3.7 Flash
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...
stepfun/step-3.7-flash
Context Size
256K
Input Price
30,000 pts/M
Output Price
172,500 pts/M
Architecture
Text
Image
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetoolstop_logprobstop_p
Details
TokenizerOther
Max Completion256,000 tokens
Provider Context256K tokens
ModeratedNo
CreatedMay 28, 2026