# How Zeta Global uses Fireworks AI

**94%**: “Report summaries stay as well grounded in customer data as the leading closed model’s, at 94% lower cost per request.”

As published on [fireworks.ai](https://fireworks.ai/customers/zeta-fine-tuned-nemotron-models-case-study), November 2026. Captured by usedby on 2026-11-06.

- Company: [Zeta Global](https://www.usedby.ai/companies/zeta-global.md)
- Tool: [Fireworks AI](https://www.usedby.ai/tools/fireworks-ai.md)
- Industry: [Marketing Tech](https://www.usedby.ai/companies/industry/marketing-tech-martech.md)
- Teams: Data & AI Lab

## The use case: how Zeta Global deploys Fireworks AI

Zeta fine-tuned open-weight NVIDIA Nemotron models on Fireworks to route requests to the right tools and to summarize reports for Athena, the AI assistant in its AthenaOS platform. The models are trained with managed supervised fine-tuning and served on dedicated deployments.

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

> Report summaries stay as well grounded in customer data as the leading closed model’s, at 94% lower cost per request.

- **six times faster**: “Zeta’s fine-tuned routing model outscored the strongest closed model on tool selection (94.7% against 89.3%) and responds six times faster.”
- **12.3%**: “In production, end-to-end answer correctness rose 12.3%.”
- **47 points**: “Fine-tuning on Fireworks lifted routing accuracy by up to 47 points.”
- **47% to 72%**: “Routing also costs 47% to 72% less per request than the strongest closed model, so Zeta can expand the usage across AthenaOS without inference spending rising in step.”

> Frontier models are excellent, and we still use them where their broader capabilities matter. But for a high-volume, repeatable domain task, a fine-tuned smaller model can deliver comparable or better quality at a lower cost per request. It can also use a shorter prompt and respond faster, which matters in an interactive product.
>
> Nate Yohannes, President of Data & AI Lab and Global Head of Research and Development, Zeta Global

Source: [fireworks.ai](https://fireworks.ai/customers/zeta-fine-tuned-nemotron-models-case-study), captured 2026-11-06.

## Fireworks AI users in Marketing Tech

- [HubSpot](https://www.usedby.ai/companies/hubspot.md) — Observed

## What usedby checked

We compared the story with its live page on 2026-11-06.

- Checked: the figure 94% is printed word for word on the page, near the name of Zeta Global.
- Checked: the passage quoted above is copied word for word from the page, near the name of Zeta Global.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Zeta Global uses Fireworks AI. Confirmed line. Latest check across sources: 2026-11-06.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/zeta-global-fireworks-ai · How we check: https://www.usedby.ai/methodology