The use case: how Decagon deploys Modal
Decagon uses Modal's infrastructure to train compact open-source models with fine-tuning and reinforcement learning, and to serve them for real-time voice AI. Modal's inference team also built a custom draft model and an asynchronous scheduler for speculative decoding in SGLang to reduce latency.
More reported results
Figures published by Decagon on its own page. They are not independently measured by usedby.
The resulting draft model achieved 38% higher accept lengths than open-source baselines, unlocking a major leap in inference efficiency.
These changes completely eliminated idle time on H200 GPUs and improved throughput by up to 12%.
Other AI tools used by Decagon
Other public relationships recorded on usedby.
Explore Decagon’s AI stackModal users in Artificial Intelligence
Companies in the same sector, with public evidence.
See all Modal customersGo straight to the source
Based on Decagon’s own page about how it uses Modal. We check the public evidence; the results are reported by the company.
decagon.ai- Source published
- Nov 5, 2025
- Last checked
- Nov 17, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 65%Checked
Printed word for word on the page, near the name of Decagon.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Decagon.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Decagon uses ModalChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Modal's infrastructure powered this progress, enabling Decagon to train and serve increasingly capable models while scaling seamlessly to meet rapidly growing traffic.












