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...
The figures
- Made by
- StepFun
- Model ID
- stepfun/step-3.7-flash
- Input
- $0.2 per million tokens
- Output
- $1.15 per million tokens
- Context window
- 262K tokens
- Longest answer
- 230K tokens
- Takes in
- text, image, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 28 May 2026
Read on 3 Oct 2026.