$0.10 per 1M input tokens and $0.30 per 1M output tokens; cached input $0.02 per 1M; cheapest via DeepInfra at $0.09 / $0.30.
There is no free API; the cheapest paid price is $0.09 per 1M input tokens.
Through the API of DeepInfra, Featherless, SiliconFlow.
256K tokens, with up to 256K output tokens.
Released 2026-04-02. It has been superseded by Step 3.7 Flash.
No, Step 3.5 Flash is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
No, it accepts text only.
Step 3.5 Flash is a closed language model from StepFun, released Apr 2026, the successor to Step 3.5 Flash.
Ling 3.0 Flash VL (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).