Skip to content

Step 3.7 Flash

by StepFun (China) · listed May 2026RTVW

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

Current rates USD per 1M tokens

Input$0.185

Output$1.11

Cache read$0.037

Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)

Output price vs. maker flagships ($/1M tokens)

On the record

Model id: step-3.7-flash
Context window: 256K tokens
Max output: 256K tokens
Input modalities: text, image, video
Output modalities: text
Reasoning: yes
Tool calls: yes
Open weights: yes
Knowledge cutoff: Mar 2026
Released: 2026-05-29
Last updated: 2026-06-29
Provider docs: platform.stepfun.com/docs/zh/overview/concept

Back of the envelope

Input M tokensOutput M tokens

≈

Also listed at

Nvidiafree in · free out
StepFun (Global)$0.185 in · $1.11 out
Ambient$0.19 in · $1.14 out
Deep Infra$0.20 in · $1.15 out
LLM Gateway$0.20 in · $1.15 out
Kilo Gateway$0.20 in · $1.15 out
OpenRouter$0.20 in · $1.15 out
ZenMux$0.20 in · $1.15 out
Hugging Face$0.20 in · $1.15 out
Vercel AI Gateway$0.20 in · $1.15 out
Eden AI$0.20 in · $1.15 out
Requesty$0.20 in · $1.15 out
DevPass (LLM Gateway)$0.20 in · $1.15 out
AIHubMix$0.22 in · $1.32 out
StepFun Step Plan (Global)— in · — out

← All StepFun (China) listings