Step-3.5-Flash: Benchmarks, Pricing & Context Window
Step-3.5-Flash is a language model from StepFun, released in February 2026.
Step-3.5-Flash is StepFun's fast, cost-effective text model optimized for quick inference. Built on their Step3 architecture, it offers strong performance across text tasks with low latency and efficient token usage, ideal for production
Step-3.5-Flash pricing
Providers
Step-3.5-Flash starts at $0.100 per million input tokens and $0.400 per million output tokens via StepFun.
| Provider | Input $/M | Output $/M | Max Input | Max Output | Latency s | Throughput | Quant | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 StepFun | $0.100 | $0.400 | 65.5K | 8.2K | 3.21 | 302 c/s | — |
Step-3.5-Flash API
API access coming soon
Step-3.5-Flash will be available through our gateway shortly.
Step-3.5-Flash examples
Recent arena outputs from Step-3.5-Flash, picked from the highest-ranked matchups.
Step-3.5-Flash license
Step-3.5-Flash is released under the Apache 2.0 license, which permits commercial use, has 196.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 196.0B
Apache License 2.0 - allows commercial use
FAQ
Common questions about Step-3.5-Flash.