Adaptive routing
Send each request to the model that answers it best, scored on live quality and cost rather than a fixed preference order.
38%median cost reduction
Now routing to self-hosted models
Ship AI features without the plumbing
Halcyon is the control plane between your product and every model you use. Route, cache, evaluate and observe from one typed API, and change providers without changing code.
- 38%
- Lower cost per request
- 11ms
- Routing overhead
- 1,200+
- Teams building
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
Platform
Everything between the request and the answer
Six systems that most teams end up building badly. They are the product, not add-ons, and every plan includes all of them.
Semantic caching
Cache on meaning, not on string equality, so paraphrased questions hit the same entry and never reach a model.
4.1xeffective hit rate
Continuous evaluation
Every deployment replays your graded set before it takes traffic, and rolls back on its own if quality drops.
2,400graded cases per run
Structured pipelines
Compose retrieval, tools and generation as a typed graph. Each node is independently versioned, cached and traced.
11msorchestration overhead
Managed retrieval
Chunking, embedding and reranking behind one endpoint, with incremental reindexing as your corpus changes.
92%recall @ 10
Policy enforcement
Redaction, jailbreak detection and per-tenant rate limits applied at the edge, before a prompt reaches a provider.
0prompts stored by default
How it fits
A day to adopt, not a quarter
Halcyon is a base URL and a key. Point your existing client at it and nothing else has to change on the first day.
Drop-in compatible
Speaks the API your SDK already speaks. Change the base URL and your calls keep working.
Versioned everything
Prompts, pipelines and routing policies are versioned artifacts you can diff, review and roll back.
Bring your own models
A self-hosted checkpoint is just another route, scored and cached like any hosted one.
Private by default
Nothing is retained unless you turn retention on. Redaction runs before a prompt leaves your VPC.
Fails to a good answer
A provider outage reroutes mid-flight. Your users see a slower response, not an error page.
One bill
Every provider, your own capacity and the platform on a single invoice, broken down per feature.
Questions
The things engineers ask first
No. Halcyon accepts the request shape your SDK already sends. Routing, caching and evaluation happen around your prompt, not to it. Prompt management exists if you want it, and is entirely optional.
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