What's new across WAVE, at the platform, workstream, and product level. Shipping in the open.
Filtered by tag routing · clear
inference.wave.online is live: one standard endpoint fronting 13 providers with measured routing, automatic failover, and per-token metering. Spend is tracked to eight decimals. The public leaderboard shows what we measured and what actually ran. The wave CLI is on npm. Every WAVE surface now serves both people and agents.
Call dispatch with an optimize_for mode of cost, balanced, or intelligence to steer which model handles a request. Available modes are configured per catalog and per team.
The large-context tier now routes to a model that scored higher in our internal evaluation, improving answer quality for that class of request.
Dated, versioned changes to the API and SDKs live at changelog.wave.online.