Silent model
From December 3, 2026, Gemini API requests for gemini-omni-1.1-flash are automatically routed to gemini-omni-1.2-flash and billed at Gemini Omni 1.2 Flash rates.
What changes
Google's November 5, 2026 changelog says that effective December 3, 2026, API requests to gemini-omni-1.1-flash will automatically route to gemini-omni-1.2-flash at Gemini Omni 1.2 Flash rates; the same entry announces gemini-omni-1.2-flash as GA. The deprecations page lists gemini-omni-1.1-flash (released August 27, 2026) with December 3, 2026 in the shutdown-date column and gemini-omni-1.2-flash as the replacement, noting that the endpoint routes API requests to gemini-omni-1.2-flash from that date. The Gemini Omni Flash model page lists gemini-omni-1.1-flash as Stable and says it routes to gemini-omni-1.2-flash on December 3, 2026. The model page gives gemini-omni-1.2-flash longer input video (up to 15s for editing, versus 10s), output video of 3s-15s (versus 3s-10s), and native audio and text output; the changelog lists 30% lower video output pricing. Google's Omni guide says the routing needs no code changes, and Google does not say any requests will fail.
Silent: No error. Behavior, results, or cost change quietly.
What to do
Before December 3, 2026, change the model string from gemini-omni-1.1-flash to gemini-omni-1.2-flash, the model Google will route your requests to from that date, and re-test your video generation and editing flows on output and cost, since a different model will answer at Gemini Omni 1.2 Flash rates.