Priority pay-per-token for Foundation Model APIs
GAVerifiedAdded Sep 22, 2026
Priority pay-per-token, also referred to as priority mode, for Foundation Model APIs pay-per-token is generally available for partner models and in preview for open source models. Priority mode is for latency-sensitive, real-time applications that need more consistent availability under load.
Topics: Streaming, Performance
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More Agent Bricks and Mosaic AI releases
Every Agent Bricks and Mosaic AI release| Date | Release | Type |
|---|---|---|
| Jul 21 | Google Gemini 3.6 Flash now available as a Databricks-hosted model Update | Update |
| Jul 21 | Google Gemini 3.5 Flash Lite now available as a Databricks-hosted model Update | Update |
| Jul 24 | Anthropic Claude Opus 5 now available as a Databricks-hosted model Update | Update |
| Jul 17 | Connect and govern any external model provider Update | Update |
| Jul 16 | MLflow trace storage in Unity Catalog will soon be available by default for workspaces with the compliance security profile enabled Update | Update |
| Jul 16 | MLflow trace storage in Unity Catalog is now generally available GA | GA |
| Jul 16 | Google Gemini 3 Pro is retired Deprecation | Deprecation |
| Jul 29 | Upcoming general availability of Unity Gateway GA | GA |
