Skip to main content
usedby

3 months

Faster launch

As published on together.ai. Checked by usedby on Oct 9, 2026.

What happened

LegionEdge uses Together Code Sandbox to run its cloud development environments in Firecracker microVMs, with file snapshots and live previews, powering an AI prototyping and development platform. It also plans to use Together's DeepSeek models and inference infrastructure for server-side code completions.

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

  • 16s“Cold starts in ~2s (vs. 16s on other platforms)”

By partnering with Together AI, LegionEdge accelerated their launch by more than three months. Instead of spending engineering cycles building custom infrastructure for VM orchestration, persistent storage, and preview rendering, they were able to focus entirely on product development.

From the page. together.ai

We originally planned to build our own VM and preview system,” Sean explained. “But Together made that unnecessary and saved us at least 3 months of work.

Sean Filimon, LegionEdge. Source

What the story claims, and what we checked

What we compared with the page.

  • The figure: 3 monthsCheckedThe figure is on the page; its label is our wording.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of LegionEdge.
  • LegionEdge uses Together AICheckedConfirmed line.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

95%“Time to First Token (TTFT): Improved by up to 95%”Arcee AI uses Together AI. Another customer of Together AI6דDecagon 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 AI