modelgrep
S

StepFun: Step 3.5 Flash

stepfun/step-3.5-flash

52nd smartest of 178Cheaper than 86% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
37.8
52nd of 178
Design Elo
Speed
46
181st fastest
Latency
406ms
first token
Input price
$0.090
43rd cheapest
Context
262K
16K max out

How it compares

Smarter than71%
of all ranked models
Faster than39%
of all ranked models
Cheaper than86%
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 · via OpenRouter
Artificial Analysis68th percentile
Intelligence Index
37.8
Coding Index
31.6
Agentic Index
52.0
GPQA Diamond
83%
Humanity's Last Exam
19%
SciCode
40%
Tau²-Bench (agentic)
94%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.090$0.30099.6%
SiliconFlowfp8$0.100$0.30099.5%

Specifications

Context window262K
Max output16K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.020/M
ModeratedNo

Step 3.5 Flash FAQ

How much does Step 3.5 Flash cost?

Step 3.5 Flash costs $0.090 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 43rd cheapest of 298 paid models.

How smart is Step 3.5 Flash?

Step 3.5 Flash scores 37.8 on the Artificial Analysis Intelligence Index, ranking 52nd of 178 benchmarked models, with a GPQA Diamond score of 83%.

How fast is Step 3.5 Flash?

Step 3.5 Flash generates around 46 tokens per second with 406ms time-to-first-token (p50), the 181st fastest tracked model.

What is Step 3.5 Flash's context window?

Step 3.5 Flash supports a 262K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head