Step 3.7 Flash
stepfun/step-3.7-flash
- context
- 262K
- modalities
- text, image, video → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Low cost
Overview
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
- DeepInfraView DeepInfra
- NovitaView Novita
- StepFunView StepFun
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| DeepInfradeepinfra | $0.16 | $0.92 |
| DeepInfradeepinfra/us | $0.16 | $0.92 |
| Novita | $0.20 | $1.15 |
| StepFun | $0.20 | $1.15 |
DeepInfra
deepinfra
- input / 1M
- $0.16
- output / 1M
- $0.92
DeepInfra
deepinfra/us
- input / 1M
- $0.16
- output / 1M
- $0.92
Novita
- input / 1M
- $0.20
- output / 1M
- $1.15
StepFun
- input / 1M
- $0.20
- output / 1M
- $1.15
Use this model
through Nautili
Route requests to Step 3.7 Flash through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.