# How Staffbase uses TrueFoundry

**141 million requests**: “the Gateway has governed more than 141 million requests”

As published on [truefoundry.com](https://www.truefoundry.com/case-studies/how-staffbase-runs-on-truefoundry). Captured by usedby on 2026-10-06.

- Company: [Staffbase](https://www.usedby.ai/companies/staffbase.md)
- Tool: [TrueFoundry](https://www.usedby.ai/tools/truefoundry.md)

## What the story says

Staffbase uses the TrueFoundry AI Gateway as a single endpoint for all of its AI inference traffic. It pools model deployments across multiple Azure subscriptions, regions and AWS Bedrock, balances load, routes by region for data residency, and attributes usage and cost by feature and team.

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

> Since going live in February, the Gateway has governed more than 141 million requests — now around 97.8M in a typical month — and processed 29.2 billion tokens (27.3B input and 1.9B output).

- **99.99998%**: “It has held availability at up to 99.99998% and success rates at 99.99%+”
- **29.2 billion tokens**: “processed 29.2 billion tokens (27.3B input and 1.9B output)”
- **141 deployments**: “balancing across 141 deployments in 9 regions”

> The Gateway became the layer every AI feature is built on. It gave us one place to run inference at scale, across every region and provider, with the reliability our customers expect — and it did it without our teams having to become infrastructure experts.
>
> Luca Ghersi, Director of Engineering @ Staffbase

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the figure 141 million requests is printed word for word on the page, near the name of Staffbase.
- Checked: the passage quoted above is copied word for word from the page, near the name of Staffbase.
- Checked: Staffbase uses TrueFoundry. Confirmed line. Latest check across sources: 2026-10-06.
- Not checked: the result itself. We quote it; we did not measure it.

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