Mixer AI
Gemini Omni 1.1 Flash vs Gemini Omni 1.2 Flash: specs and price
Gemini Omni 1.2 Flash — maximum duration: 15 s; input photos: up to 10.
When to choose Gemini Omni 1.1 Flash and when Gemini Omni 1.2 Flash
Gemini Omni 1.1 Flash
- The table shows no measurable edge for Gemini Omni 1.1 Flash: judge it by the result on your own scene.
Gemini Omni 1.2 Flash
- Maximum duration: 15 s vs 10 s for Gemini Omni 1.1 Flash
- Input photos: up to 10 vs up to 9 for Gemini Omni 1.1 Flash
- Minimum duration: 3 s vs 4 s for Gemini Omni 1.1 Flash
Key differences
Specifications
| Spec | Gemini Omni 1.1 Flash | Gemini Omni 1.2 Flash |
|---|---|---|
| Generation modes | from text / from first and last frames / from references / video editing | from text / from first and last frames / from references / video editing |
| First frame | Yes | Yes |
| Last frame | Yes | Yes |
| Input photos | up to 9 | up to 10 |
| Input videos | 1, required | 1, required |
| Minimum duration | 4 s | 3 s |
| Maximum duration | 10 s | 15 s |
| Resolutions | 360p / 720p / 1080p / 4K | 360p / 720p / 1080p / 4K |
| Aspect ratios | 9:16 / 16:9 | 9:16 / 16:9 |
| Prompt limit | 20,000 characters | 20,000 characters |
| Price (different settings) | — coins · 360p | — |
There is no shared resolution for a direct price comparison, so each price includes its setting and is not highlighted as cheaper.
Price at the same settings
What to compare visually
For a fair A/B test, use the same scene and, where both modes allow it, the same first frame. Inspect motion continuity, character and object consistency, physics and contacts, camera behavior, temporal deformation, in-clip cuts and audio synchronization.
What to inspect with Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash combines text, references, first/last frames, and video transformation in one variant.
- From text, 1–7 image references, first/last frames, or source-video transformation.
- New clips: 4, 6, 8, or 10 seconds; 360p, 720p, 1080p, or 4K; 16:9 and 9:16.
- The first/last-frame workflow cannot be mixed with the ordinary image-reference set.
- Video transformation works on a selected segment up to 10 seconds and does not treat the new-clip duration selector as a promise for edited output length.
What to inspect with Gemini Omni 1.2 Flash
Video from text, frames and references, editing and extension.
- Text: the result is created from a written description.
- First and last frame: two photos set how the clip starts and ends.
- The result length is 3 to 15 seconds.
- At most 10 photos as input.
How to run a fair comparison
- Fix the scene, the first frame (if both models accept one), the duration and the resolution.
- Judge motion, not stills: faces, hands and objects should hold across the whole clip and at cuts.
- If sound matters, listen to it separately: dialogue, effects and lip sync differ between models.
- Price a finished clip, not a second: the per-second rate times your real duration, rounded up once.
Sources
Prices, availability and specifications come from the Mixer AI catalog. This is not an independent test: try both models on the same task before choosing.
What we compare
FAQ
Which is cheaper: Gemini Omni 1.1 Flash or Gemini Omni 1.2 Flash?
The models use different settings, so a direct price comparison would be misleading: the prices of Gemini Omni 1.1 Flash and Gemini Omni 1.2 Flash are in the table, so compare for the mode you need.
How does Gemini Omni 1.1 Flash differ from Gemini Omni 1.2 Flash?
Gemini Omni 1.2 Flash — maximum duration: 15 s; input photos: up to 10.
How should I compare Gemini Omni 1.1 Flash and Gemini Omni 1.2 Flash fairly?
Fix the scene, first frame, duration and resolution. Watch the motion across the whole clip and listen to the sound separately. Price the finished clip, not one second.
Are both models available in Mixer AI?
Yes. Both models are in the Mixer AI video catalog; the launch button on the page opens Canvas on a computer and the Studio on a phone. The page exists only for models in the current catalog.
Which model is better?
There is no single winner. First rule out the model that lacks the duration, first or last frame, sound or resolution you need, then compare clips on your own scene. The table highlights only measurable differences.