OrcaRouter
AI gateway with a YAML+CEL Routing DSL that fans a request out to a panel of models and picks or fuses the result via an arbiter (best_of_n, synthesize, majority, first, tests_pass). BYOK at provider cost. OrcaRouter-Lite is the MIT self-hosted edition (model=auto); the fan-out DSL is the hosted tier.
Alternatives
4 workflows use OrcaRouter
Rebuild Fable 5's deep-research fan-out on your own keys (OrcaRouter)
Fan a research prompt out to a panel of models you choose, then fuse or judge the answers with an arbiter, in a routing DSL you version and control.
OrcaRouter for coding: judge by passing tests, not by vibes
Fan a hard coding task out to a panel and keep the candidate whose patch actually passes your tests, using the tests_pass arbiter.
OrcaRouter: only fan out when it is worth it
Gate the expensive fan-out behind a difficulty condition so easy chat stays cheap and only hard requests pay for a panel.
Build the Fugu pattern in the open: fan out, assign roles, verify
Run the idea under Fugu, a panel of models with roles and a verifier or a tests-passing arbiter, with your own keys and every hop visible, so the black box is a choice and not a lock-in.