The use case: how Descript deploys OpenRouter
Descript uses OpenRouter as its production inference layer for Underlord, its video editing agent, replacing direct integrations with several model developers. It routes requests across many models and inference providers, with per-model provider priority and automatic fallbacks, and uses it to evaluate new models quickly.
In the customer’s words
It's a perfect outsourcing thing, how to route between models. But with this explosion of open-weight models, the ability to easily integrate new models has become critical to our business.Other AI tools used by Descript
Other public relationships recorded on usedby.
Explore Descript’s AI stack
OpenRouter users in Artificial Intelligence
Companies in the same sector, with public evidence.
See all OpenRouter customers
Go straight to the source
Based on OpenRouter’s published case study. We check the public evidence; the results are reported by the vendor.
openrouter.ai- Last checked
- Oct 31, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 1–2 hoursChecked
Printed word for word on the page, near the name of Descript.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Descript.
- Descript uses OpenRouterChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
OpenRouter removed the per-model integration work that had been putting these evaluations on an engineer's queue. Descript's own agent and harness automate everything around that interface. The work no longer needs to be assigned to anyone.