AI Agent StoreStepFun · Provider documented preview
Step 5 Preview
A new routed offer for StepFun’s coding and knowledge-work model. Native documentation supports text, image and video input, tools, 1M context and 64K output. The Gateway output allowance differs; check your exact endpoint. No matched independent score is assigned.
Catalog added 2026-10-08 UTC · Checked 2026-10-15. OpenRouter addition is October 8. Gateway has an older release-metadata date; neither is treated as a verified native launch date.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: stepfun/step-5-preview. Native API ID step-5-preview accepts text, images and video; supports tools, JSON/JSON Schema and low/medium/high effort. The application provides tools and external access. The routed offer defaults to medium, but the native default is not explicitly established by the reviewed reference.
Available thinking settings: low, medium, high. We do not yet have comparable independent results for these settings. The default applied when a request omits effort is unverified.
Native and OpenRouter documentation agree on 1M context and 64K output. Gateway currently lists 1M max_tokens and text/image input; that serving declaration does not override the native 64K cap or establish video support there.
Native StepFun billing is in yuan per million tokens: ¥7 for uncached input and ¥20 for output. At 00:30 Beijing time on October 14 (October 13 at 16:30 UTC), the standard cache-read rate increased from ¥0.35 to ¥0.70. Users who called Step 5 Preview through the pay-as-you-go API before that cutoff keep ¥0.35 for later calls. Step Plan access is excluded from this change. The dollar prices shown here are separate OpenRouter quotes; they do not establish your native account rate. Your bill can also include tools, retries and charged thinking tokens. Check the offer used by your application.
Provider release and specifications ↗
Inspect the exact catalog model ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗