Step 3.7 Flash
LLM
by stepfun ·
stepfun-step-37-flash-20260528
Context window
262K
Max output
230K
Providers
3
Best input
$0.16
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...
Providers & prices
| Provider | Input $/MTok | Output $/MTok | Context | Upstream ID |
|---|---|---|---|---|
| D DeepInfra | $0.16 | $0.92 | 262K | stepfun/step-3.7-flash |
| S StepFun | $0.2 | $1.15 | 256K | stepfun/step-3.7-flash |
| NA Novita AI | $0.2 | $1.15 | 262K | stepfun/step-3.7-flash |