multimodalembedding@001
Google Vertex AI retires multimodalembedding@001 on 1 April 2027 (in 136 days).
| Provider | Google Vertex AI |
|---|---|
| Status | retiring |
| Shutdown date | |
| Replacement | none named |
| Source | https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions |
| Note | rel 2024-02-12; firm retirement date, no explicit deprecation notice |
Before 1 April 2027: move off it safely
- 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 "multimodalembedding@001" - See exactly what changes on the new model: formats, facts, tone, tool calls and settings it rejects:
llmshift compare --to <new model> - Swap the model in your code and open a pull request with the results:
llmshift upgrade --from "multimodalembedding@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 2027-03-15text-embedding-004: 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.