StepFun
Step 3.7 Flash Thinking
Newer StepFun flash model for faster agents, coding, and multimodal prompts
Model facts
- Context window
- 262K tokens
- Maximum output
- 256K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- $1.15 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video.
Observed price history
- 2026-08-24: $0.2 input / $1.15 output per 1M tokens
API providers
- NanoGPT — model id stepfun/step-3.7-flash:thinking; $0.2 input / $1.15 output per 1M tokens; provider documentation