Skip to main content
usedby
Search tools, companies

How Yutori uses Together AI

4–5x

“running 2x faster per step and at 4–5x lower inference cost”

As published on together.ai. Captured by usedby on Oct 3, 2026.

What happened

Yutori runs its proprietary browser-use model, Navigator, on Together AI's serverless inference platform. The platform serves its Scouts and Delegate agent products and its public developer API, covering both background and real-time agent workloads.

Summary written by usedby from the source page, in English. The figures are those of Together AI and Yutori, not ours.

Navigator outperforms the world's best frontier models, including Anthropic Opus and Open AI GPT, on browser-use tasks while running 2x faster per step and at 4–5x lower inference cost.

From the page. together.ai, captured Oct 3, 2026

Working with Together AI has allowed Yutori to scale without failures. That's important.

Dhruv Batra, Co-founder and Chief Scientist, Yutori, Yutori. Source, captured Oct 3, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 3, 2026.

  • The figure: 4–5xCheckedPrinted word for word on the page, near the name of Yutori.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Yutori.
  • Yutori uses Together AICheckedConfirmed line. Latest check across sources: Oct 3, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

6דDecagon achieved nearly 6× cost reduction per turn compared to closed models like GPT-5 mini.”Decagon uses Together AI. Another customer of Together AIunder two weeks“Together’s team shipped FP8, FP4, and INT4 quantized variants of the Cogito models in under two weeks”Deep Cogito uses Together AI. Another customer of Together AI70%“70% cost reduction for customers switching to open-source models on Together GPUs”Runware uses Together AI. Another customer of Together AI