Together AI(@togethercompute):Web agent economics are set by inference volume and each step is one inference call. A simple task (extract a field, fill a form, navigate a site) is 10 to 20 calls. A multi-site workflow runs into the hundreds. From @RaiseSummit last month: @abhshkdz, @yutori_ai co-founder/CEO, on how they ship Navigator at 2-5x cheaper and faster than closed models on web tasks: -> ~80% prefix cache hit rate -> Speculative decoding on smaller footprint models -> Post-training Qwen models with SFT and RL They run on Together, where customizable endpoints and auto-scaling let them A/B test new model variants in minutes.

Together AI

@togethercompute

Accelerate inference, model shaping, and pre-training on a research-optimized platform.

参加 November 2022

371 フォロー中 62.6K ファン

Together AI@togethercompute

2026.08.20 21:45

Web agent economics are set by inference volume and each step is one inference call. A simple task (extract a field, fill a form, navigate a site) is 10 to 20 calls. A multi-site workflow runs into the hundreds. From @RaiseSummit last month: @abhshkdz, @yutori_ai co-founder/CEO, on how they ship Navigator at 2-5x cheaper and faster than closed models on web tasks: -> ~80% prefix cache hit rate -> Speculative decoding on smaller footprint models -> Post-training Qwen models with SFT and RL They run on Together, where customizable endpoints and auto-scaling let them A/B test new model variants in minutes.