Rohan Paul (@rohanpaul_ai) · 2026/10/13 02:30:40
SubQ Snap 发布长上下文决策模型：线性注意力实现 384K Token 恒定算力与低延迟
Subquadratic 推出 SubQ Snap，一款专为真实企业工作设计的长上下文决策模型。该模型采用线性注意力机制，在输入长度从 100K 扩展至 384K Token 时保持每 Token 计算量恒定，显著优于传统二次方注意力的成本增长曲线。其支持多模态输入，并在 Decision Index v0.2.1 基准测试中超越竞品 Jev，以极低延迟和免费输出定价填补了短上下文分类工具与全代码库判断之间的空白。
报道全文原始报道全文
Rohan Paul (@rohanpaul_ai) · 2026-10-12 18
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.
↳ 引用 @alex_whedon (Alexander Whedon): 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:
