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.
More reported results
Figures published in Fireworks AI’s case study. They are not independently measured by usedby.
Zeta’s fine-tuned routing model outscored the strongest closed model on tool selection (94.7% against 89.3%) and responds six times faster.
In production, end-to-end answer correctness rose 12.3%.
Fine-tuning on Fireworks lifted routing accuracy by up to 47 points.
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.
In the customer’s words
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.Fireworks AI users in Marketing Tech
Companies in the same sector, with public evidence.
See all Fireworks AI customers
Go straight to the source
Based on Fireworks AI’s published case study. We check the public evidence; the results are reported by the vendor.
fireworks.ai- Source published
- Nov 3, 2026
- Last checked
- Nov 6, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 94%Checked
Printed word for word on the page, near the name of Zeta Global.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Zeta Global.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Zeta Global uses Fireworks AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Report summaries stay as well grounded in customer data as the leading closed model’s, at 94% lower cost per request.