SubQ Snap 长上下文决策模型发布，384K token 延迟 2.5 秒
Decision models deserve more attention than they get.
Subquadratic 发布 SubQ Snap，称其为面向企业工作的长上下文决策模型，支持 384K token 多模态上下文，是 Jev 的 12 倍。其延迟为最小上下文 80ms、32K 为 250ms、100K 为 660ms、384K 为 2.5 秒，输入定价 $0.05/百万 token，输出免费，前 1 万名注册用户可获 100M 免费输入 token。Rohan Paul 指出，其延迟随输入近似线性增长，而标准二次注意力在该区间成本约上升 15 倍，这使模型能一次处理 384K token 的代码、文档、日志和截图。
查看原帖Introducing SubQ Snap, the first long-context decision model for real enterprise work. Snap is the only decision model or LLM where compute per token stays constant as context grows. • 384K tokens of multimodal context, 12x larger than Jev. • 61.7 on Decision Index v0.2.1 vs Jev’s 57.9, outperforming on 13 of 16 enterprise benchmarks. •Processes 100K…
展开完整原文
Introducing SubQ Snap, the first long-context decision model for real enterprise work. Snap is the only decision model or LLM where compute per token stays constant as context grows. • 384K tokens of multimodal context, 12x larger than Jev. • 61.7 on Decision Index v0.2.1 vs Jev’s 57.9, outperforming on 13 of 16 enterprise benchmarks. •Processes 100K tokens and returns a decision in under one second. •$0.05/MM input tokens. Output is free. Available today to anyone. The first 10,000 sign-ups get 100M free input tokens. We’ll likely hit capacity fast and will add users as we add compute. Compute offers welcome 🙂. Latency will be variable as we tune the platform to this new model and category of users. Model speeds are 80ms for minimal context, 250ms for 32k, 660ms for 100k, and 2.5 seconds for 384k. Visit: https://t.co/Nc76iJF2a8
正文
当前显示原文，中文全文译文尚未就绪。
Decision models deserve more attention than they get.
look at the latency numbers on SubQ Snap from @subquadratic
660ms for 100K tokens. 2.5 seconds for 384K. that’s about 3.8x the time for 3.84x the input, which is what linear scaling looks like. with standard quadratic attention, the attention cost alone would rise about 15x over that range.
that scaling is how a decision model can hold 384K tokens of code, docs, logs and screenshots in one call, when most stop at 32K to 64K and make you chunk.
$0.05 per million input tokens, output free.
many of the existing decision models have mostly been short-context tools. 32K tokens is enough to classify a ticket, but too little to judge a change against a whole codebase. Now that changed.