The use case: how Notion deploys Fireworks AI
Notion fine-tuned smaller models with Fireworks AI to power AI features and agentic workflows that connect with tools like Slack, Jira, and GitHub, running faster than standard open-source models.
More reported results
Figures published in Fireworks AI’s case study. They are not independently measured by usedby.
we reduced latency from about 2 seconds to 350 milliseconds
Serve 100+ million users with reliable, low-latency workflows
In the customer’s words
By partnering with Fireworks to fine-tune models, we reduced latency from about 2 seconds to 350 milliseconds, significantly improving performance and enabling us to launch AI features at scale. That improvement is a game changer for delivering reliable, enterprise-scale AI.Fireworks helps us stay ahead by enabling fast iteration and the flexibility to adapt as AI agents evolve.Other AI tools used by Notion
Other public relationships recorded on usedby.
AnyscaleConfirmed
BraintrustConfirmed
CohereConfirmed
Common RoomConfirmed
DecagonConfirmed
GeminiConfirmedOther companies using Fireworks AI
Customers across industries, with public evidence.
CursorConfirmed
GensparkConfirmed
Paper InstrumentsConfirmed
PhyloConfirmed
TrilogyConfirmed
UpworkConfirmedGo 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
- Jul 25, 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: 4XChecked
Printed word for word on the page, near the name of Notion.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Notion.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Notion uses Fireworks AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Partnering with Fireworks, Notion fine-tuned smaller models that run faster and more accurately than standard open-source models.