Skip to content
llmprice

Step 3.5 Flash 2603

Updated Sep 11, 2026

262k context256k max outputreleased Apr 2, 2026Open weightsReasoningTool calling
Cheapest input
$0.1
Cheapest output
$0.3
Official
output per 1M tokens
Providers
6
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
EmpirioLabs AIopenCheapest$0.1Cheapest$0.3$0.02256k
NanoGPTopen$0.1$0.3$0.05262k
StepFun (China)open$0.1$0.3$0.02256k
StepFun (Global)open$0.1$0.3$0.02256k

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