SF·SIX / MODEL PROFILE
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...
StepFun Step 3.7 Flash costs $0.20 per 1M input tokens and $1.15 per 1M output tokens at the standard tier, the lowest default-region price among the 2 providers SF·SIX tracks, from StepFun (fp8). Cached input reads cost $0.04 per 1M tokens. Updated ; prices checked .
- Developer
- StepFun
- Input modalities
- text, image, video
- Output modalities
- text
- Context tokens
- 262,144
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.20 input / $1.15 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| Novita AIOpenRouter | $0.20 | $1.15 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| StepFunOpenRouter | $0.20 | $1.15 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.