Step 3.7 Flash
ChatStepFun
stepfun/step-3.7-flashStep 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...
9
credits / gen
About this model
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...
Technical Specifications
Provider
StepFun
Type
Chat
Context Window
256,000 tokens
Pricing
9 credits
Knowledge Cutoff
2025-02-28
Supported Languages
en, zh
Capabilities
Vision
Can process and understand images
File Support
Can read PDF, DOCX, XLSX & more
Reasoning
Chain-of-thought reasoning exposed
256K Context
Large context window for long documents
Vision (OR)
OpenRouter reports vision support