stepfuntext + image + video → text
StepFun: Step 3.7 Flash
Canonical ID: stepfun/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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.20
Completion Output (1M Tokens)
Output$1.15
Prompt KV-Cache Read (1M Tokens)
Cached$0.04
Context Window Capacity
Context256k tokens
Supported Parameters & Features
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p