Skip to main content
usedby
Search tools, companies

How Mirakl uses Anyscale

3x

“saved the company 3x in inference costs compared to using OpenAI API for all listings”

As published on anyscale.com. Captured by usedby on Oct 7, 2026.

What happened

Mirakl uses Anyscale's managed Ray platform to run fine-tuned, smaller open-source LLMs with LoRA adapters for batch inference. This automates catalog onboarding for marketplace sellers, with GPU clusters that autoscale to match traffic.

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

  • 80k+ token/sec“Consistent peak performance, handling 80k+ token/sec generations without latency.”
  • 10 million“automating onboarding for over 10 million products each month”
  • 20 GPU nodes“they can scale up to 20 GPU nodes during peak hours, but scale down to near-zero GPUs overnight”
  • 90%“By intelligently routing up to 90% of catalog traffic to LLaMA 3.1 8B”

Investing in fine-tuned open-source models and leveraging Anyscale to manage Ray orchestration saved the company 3x in inference costs compared to using OpenAI API for all listings.

From the page. anyscale.com, captured Oct 7, 2026

Using GPT-4 would have cost us more than half a million dollars per month… with Anyscale and fine-tuned LLaMA models, we brought that down by 3× while scaling to millions of products.

Arthur Delaitre, Manager of Data Science, Mirakl. 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: 3xCheckedPrinted word for word on the page, near the name of Mirakl.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Mirakl.
  • Mirakl uses AnyscaleCheckedConfirmed 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.

99%“With Anyscale, we were able to unify it into one model and reduce the cost by 99%”Attentive uses Anyscale. Another customer of Anyscale40%“That translated to a 40% cost reduction via spot automation”Bedrock Robotics uses Anyscale. Another customer of Anyscale4x“Accelerate end-to-end experimentation by 4x”Bonsai uses Anyscale. Another customer of Anyscale