step-3.7-flash
StepStar’s Flagship Language Reasoning Model
2026-05-30
'/%3e%3c/svg%3e "Model supports image analysis")
Input:
$0.2/1M tokens
Output:
$1.15/1M tokens
Bulk order? Contact your manager for exclusive deals
API Overview
The flagship multimodal reasoning model from Jueyue Xingchen. Based on a sparse MoE architecture with 198B total parameters and 11B activation parameters, it natively supports image and video understanding.
Playground
Log in to explore more features! Click to Log In
API Analytics
API Reference (1)
API Pricing
$￥ 円 ₽