Every model, one endpoint.
The full catalog, served by our engine and reachable by name through one endpoint. Request any of them with the model field — pricing is USD per million tokens, and every plan includes the whole catalog, which keeps growing. Click a model to open its card.
The largest frontier models, reachable by name through the same endpoint.
[06]Heavy, high-stakes coding. The main line of a serious session.
[05]Models that think before they answer — analysis, planning, hard problems.
[07]Capable generalists priced to carry an agent's daily traffic.
[08]Everyday coding hands for routine changes and fast loops.
[04]Huge context at small-model prices — for the jobs that eat tokens.
[02]Quick turns, glue steps, dispatch — at all-day-volume prices.
[03]Turn text into vectors — for semantic search, RAG, clustering, and dedupe.
[11]Your agent doesn't change.
Everything underneath does.
Start free · no card · Starter from $5/mo