StepFun Models
Usage
1.4B
25.7K
5 of 5
- step-3.7-flash
- step-5-preview
- step-3.5-flash
- step-3.7-flash
- step-5-preview
- step-3.5-flash
- step-2-16k
- stepfun-ai/step3
Which models that traffic went to
- Step 3.7 Flash74.8%1B
- Step 5 Preview25.2%353M
- Step 3.5 Flash<0.1%291K
- Step 3.7 Flash95.0%24.4K
- Step 5 Preview4.6%1.2K
- Step 3.5 Flash0.4%92
- Step 2 16K<0.1%7
- stepfun-ai/step3<0.1%6
All 5 StepFun Models
Open in model list| Modalities | |||||||
|---|---|---|---|---|---|---|---|
| step-5-preview | Takes text, vision, video, returns text. | 1M | 64K | $1.08$3.0888/M | $0.054/M | 31 tok/s | 4.86 s |
| step-3.5-flash | Takes text, returns text. | 256K | — | $0.11$0.33/M | — | 37 tok/s | 1.37 s |
| step-3.7-flash | Takes text, vision, video, returns text. | 256K | — | $0.22$1.32/M | $0.044/M | — | — |
| stepfun-ai/step3 | — | — | $1.1$2.75/M | — | — | — | |
| step-2-16k | — | — | $2$2/M | — | — | — |
StepFun on AIHubMix
Which StepFun model should I start with?
step-3.5-flash at $0.11/M input — the cheapest entry here that declares a token price, and it carries a 256K context. Move up to step-2-16k when answer quality matters more than cost.
Why are there several entries for the same model?
Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (stepfun-ai/…), and some differ only in capitalisation, kept so older integrations keep working.
The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.
How is cached input billed?
The Cache read column is the rate for input tokens served from the prompt cache — for example step-5-preview bills cache hits at 5% of the input rate and step-3.7-flash bills cache hits at 20% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.
Do I need a separate StepFun account?
No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.
Start calling StepFun in one line
One key, one endpoint, 908 models across 41 model authors.
