step-3.7-flash

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

LLM & Generative AI 1 model 3 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$0.200 Output$1.15 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
stepfun/step-3.7-flash	OpenRouter	256k contextmultimodalreasoning	$0.200	$1.15
stepfun/step-3.7-flash	DashScope	256k contextmultimodalreasoning	$0.200	$1.20
stepfun/step-3.7-flash	Novita	256k contextmultimodalreasoning	$0.200	$1.15

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

website 1198 · 44.0% wr
codecategories 1185 · 42.5% wr
uicomponent 1182 · 42.1% wr
dataviz 1174 · 42.9% wr
gamedev 1163 · 38.7% wr
asciiart 1154 · 44.9% wr
3d 1130 · 40.5% wr
svg 1083 · 37.3% wr

Input / Output modalities modality: text+image+video->text

text in+out
image input only
video input only

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
DashScope	stepfun/step-3.7-flash	$0.200	$1.20	—	—	—	2026-10-14 00:53:13
Novita	stepfun/step-3.7-flash	$0.200	$1.15	—	—	—	2026-10-14 00:54:15
OpenRouter	stepfun/step-3.7-flash	$0.200	$1.15	128.1 ms	—	100% available	2026-10-14 00:43:21

3 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json