Step 3.7 Flash
StepFun
Release Date
2026-05-29
Parameters
—
Context Length
256K
Modalities
image, text, video
Capability Radar
28
general
40
coding
81
reasoning
54
scienceest.
69
agents
90
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 147 | 60.0 | AA |
| General Ranking | 96 | 69.0 | AA |
| Science | 122 | 62.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Coding Index39.6
Intelligence Index30.3
Tau21.0
Gpqa0.8
Ifbench0.7
Lcr0.6
Scicode0.4
Terminalbench V2 10.4
Terminalbench Hard0.4
Hle0.2
Tau Banking0.1
LLM Stats Category Scores
No category score data available
Pricing
Input Price$0.2 / 1M tokens
Output Price$1.15 / 1M tokens
Blended Price (3:1)$0.438 / 1M tokens
Cache Read Price$0.037 / 1M tokens
Speed
Tokens/sec376.8
Time to First Token0.72s
Time to Answer6.02s
Provider Price Ranking
Provider Price Ranking
10 providers
Cheapest: StepFun (China)Most Expensive: EmpirioLabs AI
ProviderInputOutput
1StepFun (China)Cheapest
$0.185
$1.11
2StepFun (Global)
$0.185
$1.11
3Ambient
$0.19
$1.14
4StepFunPRIMARY
$0.2
$1.15
5NanoGPT
$0.2
$1.15
6OpenRouter
$0.2
$1.15
7Hugging Face
$0.2
$1.15
8ZenMux
$0.2
$1.15
9Vercel AI Gateway
$0.2
$1.15
10EmpirioLabs AI
$0.2
$1.15
Compare pricing across different API providers for this model.