Overview
step-3.7-flash is StepFun’s fast flash model and the successor to Step 3.5 Flash. It adds tool calling and runs a 256K context window with multimodal input (text, image, video) at a cheap cost band. Reach for it when you want fast, low-cost throughput with tool support and the option of image or video input.
Specs
Use this when
- You want cheap, fast throughput on bulk or high-volume tasks.
- You need tool calling on a low-cost model.
- You want image or video input without paying a premium tier.
Pick something else when
- You want the highest general quality: use
qwen-3.7-plus. - You want a strong agentic coding model: use
minimax-m3. - You want top deep reasoning: use
deepseek-r1.