# How Magicare.ai uses Baseten

**33%**: “33% reduction in cost”

As published on [baseten.co](https://www.baseten.co/resources/customers/magicare/), October 2026. Captured by usedby on 2026-10-12.

- Company: [Magicare.ai](https://www.usedby.ai/companies/magicare-ai.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)
- Industry: [HealthTech & Digital Health](https://www.usedby.ai/companies/industry/healthtech-digital-health.md)

## What the story says

Magicare runs an agentic pipeline on Baseten, using a hybrid of a dedicated deployment and Model APIs, to parse long patient referral packets and generate admission recommendations for skilled nursing facilities. The workload involves bursty, high-volume parallel requests that need low latency and high reliability.

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

> Moving from prepaid rate limits to usage-based pricing reduced costs while eliminating the days-long delays that stalled production.

- **60M**: “60M TPM of traffic handled”
- **2 days**: “2 days saved on average for every rate limit request”

> What I really care about is latency, reliability, and knowing that my account will not arbitrarily get blocked if we go over some rate limit. I need confidence we can scale without intervention.
>
> Adam Moisa, CTO

Source: [baseten.co](https://www.baseten.co/resources/customers/magicare/), captured 2026-10-12.

## What usedby checked

We compared the story with its live page on 2026-10-12.

- Checked: the figure 33% is printed word for word on the page, near the name of Magicare.ai.
- Checked: the passage quoted above is copied word for word from the page, near the name of Magicare.ai.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Magicare.ai uses Baseten. Confirmed line. Latest check across sources: 2026-10-12.
- Not checked: the result itself. We quote it; we did not measure it.

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