Veo 3.1 Lite preview shuts down Oct 22: Omni Flash on Sume
Google lists veo-3.1-lite-generate-preview shutting down October 22, 2026 with gemini-omni-1.1-flash as replacement. Sume id: gemini-omni-flash-1.1.

Google's deprecations page lists veo-3.1-lite-generate-preview shutting down October 22, 2026, with gemini-omni-1.1-flash as the recommended replacement. Sume's video docs list Gemini Omni Flash 1.1 under the catalog id gemini-omni-flash-1.1: 3 to 10 seconds, 16:9 or 9:16, with native synced audio.
Dates are from the Gemini API page and model facts from Video generation, read 2026-10-01.
Which Google models shut down on October 22?
| Model | Shutdown date | Recommended replacement |
|---|---|---|
veo-3.1-lite-generate-preview | October 22, 2026 | gemini-omni-1.1-flash |
veo-3.1-generate-preview | October 22, 2026 | gemini-omni-1.1-flash |
veo-3.1-fast-generate-preview | October 22, 2026 | gemini-omni-1.1-flash |
veo-3.0-generate-001, veo-2.0-generate-001 | June 30, 2026 | Veo 3.1 preview ids or GA models |
What does Omni Flash 1.1 take on Sume?
The docs say 3 to 10 seconds at 360p, 720p, 1080p or 4K in 16:9 or 9:16 with native synced audio. It accepts image and video input_references (no audio) and exposes video edit mode through the Video Router video_url field. Check duration limits against your Veo prompts: the range is shorter than a clip you may have planned on a different model.
How do I find the id to call?
Read GET /v1/catalog, which lists capabilities, endpoints, runtime readiness, models and pricing metadata. Sume uses bare catalog ids and never carries a provider-org prefix, so the id you send is gemini-omni-flash-1.1, not Google's string.
What should I do before October 22?
Inventory calls that use the three preview ids, re-run a few prompts on the replacement and compare output. For the earlier Veo retirements see Veo 3 shutdown.
Sources
Related posts
More in Models
- GPT Image aspect ratios for a Pinterest pin (2:3) and Instagram (4:5)
Sume lists 17 aspect ratios, including 2:3 for a Pinterest pin and 4:5 for an Instagram portrait. A model only accepts the ratios its catalog row lists.
- Grok Imagine Video 1.5 text-to-video at 1080p: xAI vs Sume
xAI lists native 1080p text-to-video for grok-imagine-video-1.5. Sume's row is image-to-video only at 480p and 720p. How the two differ and what to send.
- HappyHorse 1.0 API: what Runway lists and how to check Sume's models
Runway lists HappyHorse 1.0 at 3-15 seconds, 720p and 1080p. Sume's video docs name no such id, so read /v1/videos/models before you plan around it.
- HappyHorse 1.1 API ids: 480P to 1080P, 3 to 15 seconds
Alibaba lists happyhorse-1.1-t2v, -i2v and -r2v at 480P, 720P or 1080P for 3 to 15 seconds. Sume's catalog docs name HappyHorse 1.1 as not in the v1 catalog.
Written by Sume