Skip to main content
usedby
Search tools, companies

How NovelAI uses CoreWeave

75%

“saving 75% in cloud costs”

As published on wf.coreweave.com, October 2026. Captured by usedby on Oct 7, 2026.

What happened

NovelAI runs its 'Sigurd' storytelling model, based on GPT-J 6B, on CoreWeave's Kubernetes-based GPU infrastructure to serve AI-assisted story writing and text-adventure requests to its users. Dynamic scalers add or remove GPUs according to demand.

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

  • 3x“CoreWeave helps NovelAI serve requests 3x faster, resulting in a much enhanced user experience and significantly better performance-adjusted cost.”
  • 40K“The company officially launched in late April of 2021 and has quickly built a passionate base of more than 10K active subscribers who create daily content and 40K registered users.”

CoreWeave’s deployment architecture enables us to scale up extremely fast when there is more demand. We are able to serve requests 3x faster after migrating to CoreWeave, leading to a much better user experience while saving 75% in cloud costs.

From the page. wf.coreweave.com, captured Oct 7, 2026

CoreWeave’s deployment architecture enables us to scale up extremely fast when there is more demand. We are able to serve requests 3x faster after migrating to CoreWeave, leading to a much better user experience while saving 75% in cloud costs. For the users, this means the generation speeds will never slow down, even when there is peak load.

Eren Doğan, CEO NovelAI, NovelAI. Source, captured Oct 7, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 7, 2026.

  • The figure: 75%CheckedPrinted word for word on the page, near the name of NovelAI.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of NovelAI.
  • The numbers in our summaryCheckedEach one is printed on the page.
  • The publication dateCheckedRead from the page’s own metadata, never guessed.
  • NovelAI uses CoreWeaveCheckedConfirmed line. Latest check across sources: Oct 7, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

80%“Greater than 80% faster speed and enhanced performance results on NVIDIA GB200 NVL72”IBM uses CoreWeave. Another customer of CoreWeave1B+“1B+ Simultaneous viewers”Miris uses CoreWeave. Another customer of CoreWeave2.5x“train models 2.5x faster than previously experienced on NVIDIA H200s”Mistral AI uses CoreWeave. Another customer of CoreWeave