Skip to content
llmprice

Step 3.7 Flash

Updated Sep 11, 2026

262k context262k max outputreleased May 29, 2026Open weightsReasoningTool calling
Cheapest input
$0.185
Cheapest output
$1.11
Official
output per 1M tokens
Providers
17
offering this model
Spread
1.0×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
StepFun (China)openCheapest$0.185Cheapest$1.11$0.037256k
StepFun (Global)open$0.185$1.11$0.037256k
Ambientopen$0.19$1.14$0.03free262k
Deep Infraopen$0.2$1.15$0.04262k
Eden AIopen$0.2$1.15$0.04262k
EmpirioLabs AIopen$0.2$1.15$0.04256k
Hugging Faceopen$0.2$1.15262k
Kilo Gatewayopen$0.2$1.15$0.04256k
OpenRouteropen$0.2$1.15$0.04262k
Requestyopen$0.2$1.15$0.04262k
Vercel AI Gatewayopen$0.2$1.15$0.04256k
ZenMuxopen$0.2$1.15256k
Kenarifreefreefree256k
Kenarifreefreefree256k
Nvidiafreefreefree256k
UnoRouterfreefreefree256k
ZenMuxfreefreefree256k

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Provider1M input1M outputContext
StepFun Step Plan (China)plan256k
StepFun Step Plan (Global)plan256k