TokenCosts AI.iov1.0
Back to Models Directory
StepFunstep-3.7-flash

StepFun: Step 3.7 Flash API Pricing

Official PricingCall via OpenRouter

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, a...

Base Input Price$0.20/ 1M tokens
Base Output Price$1.15/ 1M tokens
Prompt Cache Read$0.040-80% discount
Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
StepFun Direct$0.20$1.15SupportedConnect
OpenRouter$0.20$1.15SupportedConnect

Head-to-Head Comparisons for StepFun: Step 3.7 Flash

StepFun: Step 3.7 Flash vs OpenAI: GPT-6.1 Sol$0.2/M vs $2/M
StepFun: Step 3.7 Flash vs GPT-4o (Omni)$0.2/M vs $2.5/M
StepFun: Step 3.7 Flash vs Claude 3.5 Sonnet$0.2/M vs $3/M
StepFun: Step 3.7 Flash vs DeepSeek-V3 (deepseek-chat)$0.2/M vs $0.27/M