gemini-omni-flash-preview shuts down September 30: what to change
Google's deprecations list gemini-omni-flash-preview with a 2026-09-30 shutdown and gemini-omni-1.1-flash as its replacement. What changes, and the Sume id.

If your code calls gemini-omni-flash-preview on the Gemini API, it stops working on September 30, 2026: Google's deprecations page lists that date and recommends gemini-omni-1.1-flash, released August 27, 2026, with no shutdown date announced. Change the model code, then re-test edits and extensions. On Sume the video model is gemini-omni-flash-1.1; you send Sume's own id to Sume, not Google's model code.
Dates are from Google's deprecations page and Omni page, read 2026-09-29.
Which Omni model codes are affected?
| Model code | Release | Shutdown | Replacement |
|---|---|---|---|
gemini-omni-flash-preview | 2026-06-30 | 2026-09-30 | gemini-omni-1.1-flash |
gemini-omni-1.1-flash | 2026-08-27 | No shutdown date announced | Not applicable |
What does Omni Flash do that I should re-test?
Google's Omni page describes text, image and reference-to-video, stateful multi-turn editing with previous_interaction_id, editing uploaded videos, and extension that appends a 3 to 10 second continuation. Limits it lists: video references up to 3 clips of up to 3 seconds each, audio references unsupported, and editing or extending uploaded videos is not available in the EEA, Switzerland and the UK. Re-run your edit and extension prompts after the switch.
What is the Sume id and what does it accept?
Sume lists gemini-omni-flash-1.1: 3 to 10 seconds at 360p, 720p, 1080p or 4K in 16:9 or 9:16, native synced audio, image and video input_references (no audio), and video edit through the Video Router video_url field. Sume's pricing code estimates a 5-second clip at $0.63 at 720p, $0.94 at 1080p and $1.88 at 4K; the catalog is the live source.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: omni-001" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "A single continuous shot of rain on a neon street.",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5
}'Sources
Related posts
More in Models
- Gemini Omni Flash vs Veo 3.1: which does Google recommend when
Google's video page names Gemini Omni Flash the default, Veo 3.1 for scene extension, last-frame control or legacy pipelines. Facts side by side, plus Sume ids.
- Does Sume Auto use GPT Image 2.5? What sume/auto picks for images
Sume's docs say Auto image routing continues to use Flare, GPT Image 2.5. Sume never says which family ran on a call, so pin openai/gpt-image-2.5 if it matters.
- GPT Image 2.5 Flare vs Sunburst: what each model page says
OpenAI calls Flare its model for everyday image generation and Sunburst its most capable for generation and editing. What each page lists, and both ids on Sume.
- GPT Image 2.5 quality levels: low, medium, high, xhigh, max and auto
GPT Image 2.5 has six quality values: auto, low, medium, high, xhigh and max. What each does to price on Sume and which one runs when you send nothing.
Written by Sume