The use case: how Cresta deploys Fireworks AI
Cresta uses Fireworks AI infrastructure to host its Ocean-1 model, a Mistral-based model, with many customer-specific LoRA adapters on a single cluster. This powers Knowledge Assist, which gives contact center agents real-time retrieval-augmented guidance.
In the customer’s words
Being able to serve the best models with cutting-edge latency provides us with an enormous competitive advantageFireworks' Multi-LoRA capabilities align with Cresta's strategy to deploy custom AI through fine-tuning cutting-edge base models. It helps unleash the potential of AI on private enterprise data.Other AI tools used by Cresta
Other public relationships recorded on usedby.
Explore Cresta’s AI stack
Other companies using Fireworks AI
Customers across industries, with public evidence.
CursorConfirmed
GensparkConfirmed
GumloopConfirmedInnovative SolutionsConfirmed
NotionConfirmed
Paper InstrumentsConfirmedGo 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
- Dec 8, 2024
- Last checked
- Nov 11, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 100xChecked
Printed word for word on the page, near the name of Cresta.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Cresta.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Cresta uses Fireworks AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Significant cost reduction: By serving multiple adapters through a single base model, Cresta achieves up to a 100x cost reduction compared to GPT-4.*