Vendor
StepFun models
2 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
2
0 routable here
Median list price
$0.29
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every StepFun model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Step 3.7 Flashstepfun/step-3.7-flash | May 28, 2026 | 262K | $0.20 | $1.15 | - | reasoning tools open weights |
| Step 3.5 Flashstepfun/step-3.5-flash | Jan 29, 2026 | 262K | $0.10 | $0.30 | - | reasoning tools open weights |
Frequently asked
- What is the cheapest StepFun model?
- Step 3.5 Flash at $0.10 per 1M input tokens and $0.30 per 1M output tokens (vendor list price).
- Which StepFun model has the largest context window?
- Step 3.7 Flash accepts 262K tokens of context.
- How do I route to StepFun models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example stepfun/step-3.7-flash); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route StepFun with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a StepFun flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.