stepfun
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...
Quality Score
100/100
price + capability + benchmarks
Input Price
$0.20
per 1M tokens
Output Price
$1.15
per 1M tokens
Context Window
256,000
tokens
- Model ID
- stepfun/step-3.7-flash
- Vendor
- stepfun
- Tokenizer
- Other
- Input Modalities
- text, image, video
- Output Modalities
- text
- Max Output
- 256,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no