Models / StepFun / Step 3.5 Flash 2603

StepFun

Step 3.5 Flash 2603

StepFun flash model for efficient multimodal reasoning, coding, and tool use

$0.10 in · $0.30 out

per 1M tokens · first-party price. Reference price from StepFun, the lab's own listing.

Context
256,000
Max output
256,000
Cache read
$0.02
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Apr 2, 2026
Updated in source
Apr 2, 2026
Knowledge
2025-01
Providers
5

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
EmpirioLabs AI$0.10$0.30$0.02——
NanoGPT$0.10$0.30$0.05——
StepFunreference$0.10$0.30$0.02——
StepFun Step Plan—————
StepFun Step Plan—————