The LLM router that belongs to you. Free credits for developers worldwide.
, /PRNewswire/ — Today, Continuum AI released OrcaRouter and OrcaRouter Lite — a unified inference layer that routes across 200+ frontier and open-source language models, with zero markup on BYOK traffic.
While OpenRouter and other incumbents charge a 5% spread on every token, OrcaRouter charges nothing. Developers bring their own keys. They pay providers directly. Continuum monetizes higher up the stack — caching, governance, SSO, audit, policy. The team puts it bluntly: the data plane is free. The control plane is the product.
“Routers shouldn’t be tollbooths. They should be infrastructure that evolves with the traffic running through it.“
What ships today:
- OrcaRouter Lite — fully open-source, MIT-licensed, self-hostable. SQLite default. No Postgres, no Redis, no Kubernetes. Runs on a laptop, a VPS, or a cluster. 127 tests passing.
- OrcaRouter (hosted) — accelerated inference, sub-50ms failover, adaptive prompt-aware routing that learns from real traffic
- Unified billing + BYOK — one invoice across OpenAI, Anthropic, Google, Mistral, DeepSeek, and 100+ models. Keys stay yours, encrypted at rest with AES-256-GCM.
- Free credits, globally — distributed to AI developers and indie builders. No card required.
The release reflects Continuum’s broader thesis: that infrastructure compounds, that the substrate beneath models will outlast the models themselves, and that the next decade of AI is won by whoever quietly owns the rails.
OrcaRouter is the opening move. What comes next has not been disclosed.
100+ models. 1 router. Zero markup. Your keys. Your cache. Every provider.
Available now at github.com/Continuum-AI-Corp/OrcaRouter-Lite. Hosted access and free credits at OrcaRouter.ai.
About Continuum AI
Continuum AI is a research and infrastructure lab working on long-horizon problems in artificial intelligence. Inquiries: Chris Zhang, +16506097501, [email protected].
SOURCE Continuum AI
