Gemini Omni Flash 1.1AI video generator
Google's fast video model, from 360p to 4K. On Leap, it sits beside 174 other models in one studio.
- Text to video
- Image to video
- Up to 10 s
- Up to 1080p
- 16:9 and 9:16
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
AI video generator
Gemini Omni Flash 1.1 at a glance
Gemini Omni Flash 1.1 is a video model from Google. It makes video from words, a first frame or a last frame, 3 to 10 seconds long, at up to 4k.
- Made by
- Makes
- Video
- Starts from
- Words, a first frame or a last frame
- Length
- 3 to 10 seconds
- Resolution
- 360p, 720p, 1080p or 4k
- Shapes
- 16:9, 9:16
- Prompt
- Up to 10,000 characters
- Price per run
- $0.123 to $3.80
- Run time
- About 24 seconds
- Updated
- October 3, 2026
How it's made
From an idea to a film, in one place.
"Basement show", replayed step by step: Seedream 5.0 Pro makes the still, Gemini Omni Flash 1.1 brings it to life. Two models, one studio.
- 01Seedream 5.0 ProMakes the stillDone
Live concert photograph, 16mm wide lens, handheld from inside the crowd, 1/30 s with motion blur and red flare. A packed, sweaty basement punk show in...
- 02Gemini Omni Flash 1.1Brings it to lifeDone
One continuous handheld shot with no cuts, from inside the pit, staying on the singer. The singer screams the chorus into the microphone held in both...
"Basement show", made on Leap: two models, one studio, one library.
Made on Leap
More from Gemini Omni Flash 1.1
Passo Giau
The yellow coupe accelerates out of the hairpin and climbs the switchback toward the camera; the drone tracks backward and rises, revealing the valley filled with low cloud and the sunlit peaks. The engine note echoes off the rock walls. Sound: the engine note echoing off the rock walls, wind.
Burner
The pilot fires the burner in two long blasts, flame roaring and heat shimmer rippling the view; the balloon rises and the valley drops away below; the wife points at a passing balloon and laughs and her husband squeezes her hand. Camera holds in the basket corner with a gentle sway. Sound: burner roar, wind, the couple laughing.
5 da manhã, shot 1
The yellow tram rattles past the camera and clears the frame, revealing the dancer already moving: he drops into fast Afro-house footwork under the streetlight, arms loose. Handheld camera, slight sway. Sound: tram bell and rattle, sneakers on cobbles.
Hot pot
She tips her head back and catches snowflakes on her tongue, laughs, then splashes the bald man beside her, who splutters and laughs too; steam swirls; the street lamp flickers on. Camera at water level, still. Sound: water lapping, laughter, the muffled city in the snow.
Dawn run, Iten
The pack runs straight toward the long lens, the girl holding the lead with long easy strides, the men behind her breathing hard; focus stays on her as they come closer; red dust drifts through the low sun. Sound: rhythmic footfalls on dirt, heavy breathing, birdsong, a distant rooster. No music.
Basement show
5 da manhã, shot 1
Away to me
Burner
Pick the right one
Gemini Omni Flash 1.1 and its siblings
| Model | Best for | Length | Resolution | Price per run |
|---|---|---|---|---|
| Gemini Omni Flash 1.1 (this page) | Google's fast video model, from 360p to 4K. | 3 to 10 seconds | Up to 4k | $0.123 to $3.80 |
| Gemini Omni Flash 1.1 Edit | Edits a video from a plain instruction and keeps the rest of the scene, from 360p to 4K. Billed by the length of the video. | – | Up to 4k | $0.135 a second of your video |
| Gemini Omni Flash 1.1 Reference | Gemini Omni Flash from up to ten reference images: the people, products and places in them, in a new shot, from 360p to 4K. | 3 to 10 seconds | Up to 4k | $0.123 to $3.80 |
Side by side
More video models on Leap
No prompt needed
Or start from a recipe
Recipes write the prompt for you: add a photo, pick a look, and get a finished result.
Questions
Gemini Omni Flash 1.1, answered
- What is Gemini Omni Flash 1.1?
- Gemini Omni Flash 1.1 is a video model from Google. Google's fast video model, from 360p to 4K. On Leap it runs in one studio beside every other top model, with one account.
- Can Gemini Omni Flash 1.1 start from a photo?
- Yes. Gemini Omni Flash 1.1 starts from words, a first frame or a last frame. The photo becomes the first frame, cropped to the video's shape.
- How long can the videos be?
- 3 to 10 seconds. You choose the length before you press go, and the price follows it.
- What resolution and sizes does it make?
- Up to 4k, in 16:9 or 9:16.
- How is it different from Gemini Omni Flash 1.1 Edit and Gemini Omni Flash 1.1 Reference?
- Gemini Omni Flash 1.1: Google's fast video model, from 360p to 4K. Gemini Omni Flash 1.1 Edit: Edits a video from a plain instruction and keeps the rest of the scene, from 360p to 4K. Billed by the length of the video. Gemini Omni Flash 1.1 Reference: Gemini Omni Flash from up to ten reference images: the people, products and places in them, in a new shot, from 360p to 4K. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- An 8-second 720p clip costs $1.08 at the default settings. By length and resolution, a run costs $0.123 to $3.80. You see the exact price before you press go, and a run that fails costs nothing.
- Is Gemini Omni Flash 1.1 free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.123 (a 3-second 360p clip), so $5 covers 40 of those. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as google/gemini-omni-flash-1.1, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need a Google account?
- No. Leap sends your request to Google's model and gives you what it makes. One Leap account runs Gemini Omni Flash 1.1 and every other model, in the studio, through the API and from your agents.
Your idea, Gemini Omni Flash 1.1.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with Gemini Omni Flash 1.1For developers
Run Gemini Omni Flash 1.1 from code
- Model ID
- google/gemini-omni-flash-1.1
- Makes
- Video
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "google/gemini-omni-flash-1.1", "input": { "prompt": "At the farmer'\''s whistle the collie springs forward and runs a wide arc up the hill to the left, flattening into the grass; the sheep bunch and turn downhill together; the farmer lowers his hand. Long lens, slight handheld drift. Sound: wind, rain, a sharp two-note whistle, sheep bleating." } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"