About

We're the aggregator every multi-model team ends up building anyway.

Every serious AI team ends up building the same four primitives internally — per-customer keys, cost tags, replay for model swaps, and eval-driven routing. They take six months, they're brittle, and they break the moment a new frontier model lands. We ship them as an API so you don't have to.

What we are

A model aggregator.
With teeth.

One OpenAI-compatible endpoint across every major lab. Plus the primitives only the aggregator can build — because they all compare across models, and a single provider SDK physically can't.

IN SCOPE
Aggregating every frontier + open-weight model under one schema. Eval-driven routing, replay + shadow A/B, sub-account API, cost tags, hard budget caps, semantic cache.
OUT OF SCOPE
We don't ship vertical apps. No packaged voice agents, no RAG-as-a-service, no coding copilots. Our customers build those on top of us.
The pitch

Built so a coding agent can use it without a human in the loop.

Every endpoint is OpenAI-compatible, every model is in one schema, and the entire capability surface is described in /llms.txt, /openapi.json, and /agents.md. A capable agent reads those once and can call every modality, mint sub-accounts, tag cost, and replay requests — without anyone editing config. The dashboard is for humans who want to look. The API is for the agent that's actually shipping.

For coding agentsRead the reference