StepFun: Step 3.5 Flash
stepfun/step-3.5-flash
96th smartest of 182Cheaper than 85% of paidReasoningTools
Intelligence
26.0
96th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.100
49th cheapest
Context
262K
66K max out
How it compares
Smarter than47%
of all ranked models
Cheaper than85%
of all ranked models
Overview
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis70th percentile
Intelligence Index
26.0
GPQA Diamond
83%
Humanity's Last Exam
23%
SciCode
39%
Tau²-Bench (agentic)
87%
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| SiliconFlowfp8 | $0.100 | $0.300 | 262K | 100% |
Specifications
Context window262K
Max output66K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsstepfun-ai/Step-3.5-Flash ↗
Step 3.5 Flash FAQ
How much does Step 3.5 Flash cost?
Step 3.5 Flash costs $0.100 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 49th cheapest of 332 paid models.
How smart is Step 3.5 Flash?
Step 3.5 Flash scores 26.0 on the Artificial Analysis Intelligence Index, ranking 96th of 182 benchmarked models, with a GPQA Diamond score of 83%.
What is Step 3.5 Flash's context window?
Step 3.5 Flash supports a 262K-token context window and can output up to 66K tokens. It accepts text input.