AI model · StepFun
Step 3.7 Flash
Model ID: stepfun/step-3.7-flash
- Input
- $0.20 per 1M tokens
- Output
- $1.15 per 1M tokens
- Context
- 262K tokens at once
- Max output
- 230K tokens per reply
- Released
- 28 May 2026 StepFun
What it can do
- YesReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- NoFree to use
Takes text, image, video; gives text.
How its listing describes it
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...
Sources
- StepFun: Step 3.7 Flash on OpenRouter — read 2 Oct 2026