# How Genspark uses Fireworks AI

**50%**: “leading to a 50% cost reduction and superior answer quality”

As published on [fireworks.ai](https://fireworks.ai/customers/genspark-deep-research-agent-rft), October 2025. Captured by usedby on 2026-10-31.

- Company: [Genspark](https://www.usedby.ai/companies/genspark.md)
- Tool: [Fireworks AI](https://www.usedby.ai/tools/fireworks-ai.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)

## 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.

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

> 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.

- **12%**: “Genspark achieved 12% better quality and 33% more tool calls than a state of the art (SOTA) closed-source model”
- **33%**: “with the RFT optimizations unlocked a 33% jump in tool calls”
- **4 weeks**: “deploy a complex optimized solution from POC to Production in 4 weeks”

> 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.
>
> Kay Zhu, CTO

Source: [fireworks.ai](https://fireworks.ai/customers/genspark-deep-research-agent-rft), captured 2026-10-31.

> Fireworks enabled us to own our AI journey, and unlock better quality in just four weeks.
>
> Kay Zhu, CTO

Source: [fireworks.ai](https://fireworks.ai/), captured 2026-10-05.

## Other AI tools used by Genspark

- [Claude](https://www.usedby.ai/tools/claude.md) — Confirmed
- [E2B](https://www.usedby.ai/tools/e2b.md) — Confirmed
- [OpenAI API](https://www.usedby.ai/tools/openai-api.md) — Observed
- [fal](https://www.usedby.ai/tools/fal.md) — Observed

## Fireworks AI users in Artificial Intelligence

- [Gumloop](https://www.usedby.ai/companies/gumloop.md) — Observed
- [Lightfern](https://www.usedby.ai/companies/lightfern.md) — Observed
- [Lovable](https://www.usedby.ai/companies/lovable.md) — Observed
- [Micro 1](https://www.usedby.ai/companies/micro-1.md) — Observed
- [Motif](https://www.usedby.ai/companies/motif.md) — Observed
- [NinjaTech AI](https://www.usedby.ai/companies/ninjatech-ai.md) — Observed

## What usedby checked

We compared the story with its live page on 2026-10-31.

- Checked: the figure 50% is printed word for word on the page, near the name of Genspark.
- Checked: the passage quoted above is copied word for word from the page, near the name of Genspark.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Genspark uses Fireworks AI. Confirmed line. Latest check across sources: 2026-10-31.
- Not checked: the result itself. We quote it; we did not measure it.

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