Models / StepFun / Step 3.7 Flash

StepFun

Step 3.7 Flash

Newer StepFun flash model for faster agents, coding, and multimodal prompts

$0.19 in · $1.11 out

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

Provider input prices run from $0.19 to $0.22 per 1M tokens. Output prices run from $1.11 to $1.32.

Context
256,000
Max output
256,000
Cache read
$0.037
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
May 29, 2026
Updated in source
May 29, 2026
Knowledge
2026-03-01
Providers
21

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. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
StepFun$0.19$1.11$0.037——
StepFunreference$0.19$1.11$0.037——
Ambient$0.19$1.14$0.03$0—
Deep Infra$0.20$1.15$0.04—deprecated
DevPass$0.20$1.15$0.04——
Eden AI$0.20$1.15$0.03——
EmpirioLabs AI$0.20$1.15$0.04——
Hugging Face$0.20$1.15———
Kilo Gateway$0.20$1.15$0.04——
LLM Gateway$0.20$1.15$0.04——
NanoGPT$0.20$1.15$0.04——
Novita AI$0.20$1.15$0.04——
OpenRouter$0.20$1.15$0.04——
Requesty$0.20$1.15$0.04——
Vercel AI Gateway$0.20$1.15$0.04——
ZenMux$0.20$1.15———
AIHubMix$0.22$1.32$0.044——
Kenari$0$0———
StepFun Step Plan—————
StepFun Step Plan—————
UnoRouter$0$0———