Yutori's browser-use agents run in tight loops: screenshot, action, repeat, dozens of times per task. On Together AI, their Navigator model beats frontier performance at 2x faster inference and 4-5x lower cost.

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.

#CSF26# Don't miss our guest illustrators, lack and Yukoring, they will be appearing on stage over the next two days! Suntec Singapore, see you this weekend! 🎟️ Grab your tickets via