Step 3.7 Flash
by Nvidia · listed May 2026RTVW
StepFun flash model for efficient multimodal reasoning, coding, and tool use
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
stepfun-ai/step-3.7-flash- Context window
- 256K tokens
- Max output
- 16K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-05-28
- Last updated
- 2026-05-28
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- Requesty$0.18 in · $1.03 out
- StepFun (Global)$0.185 in · $1.11 out
- StepFun (China)$0.185 in · $1.11 out
- Ambient$0.19 in · $1.14 out
- Deep Infra$0.20 in · $1.15 out
- Hugging Face$0.20 in · $1.15 out
- OpenRouter$0.20 in · $1.15 out
- ZenMux$0.20 in · $1.15 out
- Vercel AI Gateway$0.20 in · $1.15 out
- Eden AI$0.20 in · $1.15 out
- Kilo Gateway$0.20 in · $1.15 out
- StepFun Step Plan (China)— in · — out
- StepFun Step Plan (Global)— in · — out