veo-3.1-generate-001
veo-3.1-generate-001 is active. Google Vertex AI will not retire it before 17 November 2026. Replacement: gemini-omni-1.2-flash.
| Provider | Google Vertex AI |
|---|---|
| Status | active |
| Shutdown date | not announced |
| Not retired before | 2026-11-17 |
| Replacement | gemini-omni-1.2-flash |
| Source | https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions |
| Note | rel 2025-11-17; not_before:2026-11-17 |
When it retires, be ready
- Find every call to it in your code (Python, JS/TS, Go, Java, configs, notebooks), with nothing to install:
uvx llmshift scan - Turn your real traffic into tests, so you compare on what your users send:
llmshift snapshot logs/ --model "veo-3.1-generate-001" - See exactly what changes on the replacement: formats, facts, tone, tool calls and settings it rejects:
llmshift compare --to gemini-omni-1.2-flash - Swap the model in your code and open a pull request with the results:
llmshift upgrade --from "veo-3.1-generate-001" --apply --compare --pr
Then llmshift init --github keeps the check on every pull request. LLMShift is free and open source (MIT) and runs on your machine.
Other Google Vertex AI retirements
gemini-3.6-flash: retires 2026-11-19claude-sonnet-4-5: retires 2026-11-30gemini-live-2.5-flash-native-audio: retires 2026-12-13gemini-3.7-flash: retires 2027-01-28gemini-2.5-flash-image: retires 2027-03-15multimodalembedding@001: retires 2027-04-01
Wrong date or replacement? Tell us on GitHub, with a link to the provider's page.
Lifecycle data updated 2026-11-14, collected from the providers' official deprecation pages. Dates can move: check the source before you plan around one. Visits are counted with GoatCounter, which sets no cookies.