# How Onepot AI uses Anyscale

**50%**: “including running 50% of workloads on spot instances for cost efficiency”

As published on [anyscale.com](https://www.anyscale.com/resources/case-study/onepot-ai). Captured by usedby on 2026-10-07.

- Company: [Onepot AI](https://www.usedby.ai/companies/onepot-ai.md)
- Tool: [Anyscale](https://www.usedby.ai/tools/anyscale.md)
- Teams: ML

## What the story says

onepot uses Anyscale as its distributed compute platform to enumerate tens of billions of candidate reactions and score them with feasibility ML models on CPU and GPU instances. This filters the space down to compounds likely to synthesize successfully, running inside its own AWS and GCP accounts with part of the workload on spot instances.

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

> Because Anyscale handles interruptions automatically, we can roughly cut our compute bill in half by using spot instances with zero engineering on our side.

- **70 to 80 percent**: “The result is onepot CORE: more than 3 billion synthesizable compounds with a 70 to 80 percent synthesis success rate, guaranteed 90% or better purity by LC/MS, and delivery timelines as short as five business days.”

> Because Anyscale handles interruptions automatically, we can roughly cut our compute bill in half by using spot instances with zero engineering on our side.
>
> Andrei Tyrin, Co-founder, onepot AI

## What usedby checked

We compared the story with its live page on 2026-10-07.

- Checked: the figure 50% is printed word for word on the page, near the name of Onepot AI.
- Checked: the passage quoted above is copied word for word from the page, near the name of Onepot AI.
- Checked: Onepot AI uses Anyscale. Confirmed line. Latest check across sources: 2026-10-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/onepot-ai-anyscale · How we check: https://www.usedby.ai/methodology