Skip to content
Dashboard

StepFun 3.5 Flash

StepFun 3.5 Flash is an open-source sparse MoE reasoning model from StepFun with 196B total parameters and about 11B active per token. It supports a context window of 262.1K tokens and a max output of 262.1K tokens per request.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'stepfun/step-3.5-flash',
prompt: 'Why is the sky blue?'
})

More models by StepFun

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
256K
6.5s
170tps
$0.20/M$1.15/M
Read:$0.04/M
Write:
+2
stepfun logo
05/28/2026