Output tokens cost $0.33 per million on step-3.5-flash and $1.32 per million on step-3.7-flash. Input tokens cost $0.11 per million on step-3.5-flash and $0.22 per million on step-3.7-flash. Cached input tokens are billed at $0.11 per million on step-3.5-flash and $0.04 per million on step-3.7-flash. Context lengths are 256,000 tokens on step-3.5-flash and 256,000 tokens on step-3.7-flash.
step-3.5-flashstep-3.7-flashstep-3.5-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.
step-3.7-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
step-3.5-flash: $0.33/M output tokens; step-3.7-flash: $1.32/M. Use the cost calculator above to estimate your own workload.
step-3.5-flash accepts 256,000 and step-3.7-flash accepts 256,000 input tokens.
step-3.5-flash accepts text and image input; step-3.7-flash accepts text and image input.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix