Changelog v4.9 feature 24 July 2026

Dedicated capacity in eleven regions

You can now reserve a replica for a single workload in any region marked dedicated on the network page. A reserved replica is never shared, never cold, and billed monthly rather than per token.

The reservation is a line in your deployment config, not a sales call.

Put the model next to the user.

One command, thirty-one regions, and an invoice that matches what you actually served.