Step 3.7 Flash

StepFun· released 28 May 2026

stepfun/step-3.7-flash

Input / 1M tokens: $0.2
Output / 1M tokens: $1.15

Context window262K tokens

Longest answer: 230K tokens

reads textreads imagereads videoopen weightstool callingvisionreasoning

About

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...

Details

Lab: StepFunopenrouter.ai · 3 Oct 2026
Context: 262Kopenrouter.ai · 3 Oct 2026
Input price: $0.2 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $1.15 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 230,400 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, image, videoopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list

Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Auto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Grok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Grok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Pareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Llama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Longest-Context Models in 2026466 listed
Newest Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed

Sources

openrouter.ai/stepfun/step-3.7-flash· checked 3 Oct 2026