The use case: how Genspark deploys Fireworks AI
Genspark uses Fireworks' Reinforcement Fine Tuning on the open Kimi K2 model to power its Deep Research agent, which runs multi-step, multi-tool research and produces structured reports. The fine-tuned model replaced a closed-source frontier model and is deployed on Fireworks infrastructure.
More reported results
Figures published in Fireworks AI’s case study. They are not independently measured by usedby.
Genspark achieved 12% better quality and 33% more tool calls than a state of the art (SOTA) closed-source model
with the RFT optimizations unlocked a 33% jump in tool calls
deploy a complex optimized solution from POC to Production in 4 weeks
In the customer’s words
We are really excited to see what we were able to achieve partnering with Fireworks. Fireworks enabled us to own our AI journey, and unlock better quality in just four weeks. This resulted in a better user experience for our customers.Fireworks enabled us to own our AI journey, and unlock better quality in just four weeks.Other AI tools used by Genspark
Other public relationships recorded on usedby.
Explore Genspark’s AI stack
Fireworks AI users in Artificial Intelligence
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
- Oct 31, 2025
- Last checked
- Oct 31, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 50%Checked
Printed word for word on the page, near the name of Genspark.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Genspark.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Genspark uses Fireworks AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
By leveraging Fireworks’ Reinforcement Fine Tuning to train large state-of-the-art open models, in one month Genspark achieved 12% better quality and 33% more tool calls than a state of the art (SOTA) closed-source model , leading to a 50% cost reduction and superior answer quality.