Step 3.5 Flash is StepFun's language model with a 262K context window and up to 16K output tokens, available from 2 providers, starting at $0.09 / 1M input and $0.3 / 1M output. An open-source Mixture-of-Experts reasoning model from StepFun with 196B total parameters (11B active), featuring a 256K context window and tool-calling support.
Specifications
Canonical IDstep-3-5-flash
TypeLanguage
StatusActive
CreatorStepFunStepFun
Providers
Context Window262K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters199B
HuggingFace Likes783
HuggingFace Downloads (30d)147,877
HuggingFace Downloads (all-time)532,020
Release Date · 5 months ago
Benchmarks
Intelligence Index
25.5
#117
GPQA
0.8
#82
HLE
0.2
#74
IFBench
0.6
#88
Time to First Token
0.87s
#314
SciCode
0.4
#121
LCR
0.4
#170
TerminalBench Hard
0.3
#108
TAU2
0.9
#71
Output TPS

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write 5m
$ / 1M
OpenRouter logo
OpenRouter
stepfun/step-3.5-flash
$0.09$0.3$0.02N/A
Vercel AI Gateway logo
Vercel AI Gateway
stepfun/step-3.5-flash
$0.09$0.3N/A$0.02

Cost Calculator

US Dollar ($)
Preset:

Model IDs

step-3-5-flash
step-3-5-flash-0202
stepfun-ai/Step-3.5-Flash
stepfun/step-3.5-flash