About
We build the boring layer under the interesting part
A team of infrastructure engineers who kept rebuilding the same routing and evaluation stack, and decided to make it once, properly.
Why Halcyon
The model is the easy part
Getting a good answer from a model takes an afternoon. Getting a good answer every time, at a price you can defend, from a provider you can replace, is the part that takes a year.
Halcyon is that year, already done. It sits between your product and the models, and it is the only thing your code talks to.
One API across every provider and your own weights
Quality measured continuously, not argued about
Costs that fall as the router learns your traffic
No prompt or completion stored unless you ask
Story
Built because we kept building it
2022
The third rewrite
Two of us had built the same routing and evaluation layer at three companies. We stopped and wrote it once.
2023
First production traffic
A support product moved its whole inference path across in an afternoon. It is still running on it.
2024
Evaluation shipped
Replaying a graded set before every deploy turned out to matter more than routing. It became the default.
2025
Self-hosted models
The router stopped caring where a model lives. Your own weights on your own hardware became one more route.
41
Engineers
9
Countries
1,200+
Teams building
99.99%
Uptime, trailing year
Contact
Tell us what you are building
An engineer reads every message. If you are moving an existing workload across, mention the provider and we will send the migration notes for it.
engineering@halcyon.dev
Docs
docs.halcyon.dev
Status
status.halcyon.dev
Office
Lisbon, remote-first