Skip to content

Google shuts down Veo 3.1 preview and Gemini Omni Flash preview today

Four preview model IDs in the Gemini API stop working on 22 October, with Google pointing every one of them to the same replacement: gemini-omni-1.1-flash.

Source: Google

Google’s Gemini API deprecations page shuts down four preview model IDs today, 22 October: veo-3.1-generate-preview, veo-3.1-fast-generate-preview, veo-3.1-lite-generate-preview and gemini-omni-flash-preview.

The three Veo 3.1 models were video generation previews, the first two released on 15 October 2025 and the lite version on 31 March 2026. Google’s page points all four retiring IDs, video and otherwise, to the same replacement: gemini-omni-1.1-flash.

Why it matters: if any of these model IDs are hardcoded into a pipeline, calls made from today onward will fail. Since every retiring model funnels into one replacement, the fix is a single find-and-replace, but it’s worth testing output quality rather than assuming a flash-tier successor behaves identically to a dedicated video model.

The caveat: the deprecations page gives the date but not the failure mode, so it’s unclear whether the old IDs return a clean error or just stop responding.

Share

Related reading

ML for Web Devs

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

More from The Wire

All briefs