Gemini Omni 1.1 Flash. Short clips with sound, from text or a still.
Google's Gemini Omni 1.1 Flash renders 3 to 10 second clips with audio in landscape or vertical, from a prompt or an opening frame.
- 3 to 10 second clips
- 16:9 and 9:16
- Native audio
- First and last frame control
Gemini Omni 1.1 Flash is a video model from Google that takes a prompt, and optionally a first and last frame, and returns a 3 to 10 second clip with sound in 16:9 or 9:16. It is priced per second by resolution: OpenRouter lists about 3.4 cents a second at 360p, 10 cents at 720p and 30 cents at 4K, audio included.
In our test a 3 second 360p clip rendered in about 30 seconds and billed exactly the listed 10 cents. With no resolution set it came back 720 by 1280 at 24 frames a second with a quiet ambient track. On Treza it is a model in the Video Generation node, and you can ask for it by name in chat.
Cheap drafts at 360p
About 3.4 cents a second at its lowest tier, so a 3 second test shot costs 10 cents. Move the keeper up a tier once the direction is right.
Sound in every clip
Every clip comes back with an audio track, so ambience lands with the picture instead of in a separate step.
Start and end frames
Give it an opening image, a closing one, or both. Describe the image in the prompt: in our test a prompt about something else led it away from the still.
Landscape or vertical
16:9 or 9:16 at 3 to 10 seconds, for a cutaway, a social beat or a shot in a longer Sequence.
What to make with Gemini Omni 1.1 Flash
Real prompts, and what comes back. Every one runs in Treza chat or as a node on the canvas.
“A barista pours steamed milk into a latte, slow push-in, vertical”
A short vertical shot with cafe ambience.
“This product photo (attached): sunlight drifts across it, gentle push-in”
A still brought to life, opening on your frame.
“Waves roll onto a rocky beach at dusk, wide, 8 seconds”
An establishing shot with the sound of the sea.
“A cat jumps onto a windowsill and looks outside, 5 seconds”
A small story beat for a series.
“From this sketch (first frame) to this finished painting (last frame)”
A transition between two images you supply.
“Rain on a neon street at night, slow dolly forward, 360p draft”
A cheap draft before a final at a higher tier.
Gemini Omni 1.1 Flash is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Gemini Omni 1.1 Flash
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Gemini Omni 1.1 Flash as an API, priced per clip
The Gemini Omni 1.1 Flash API
Build a pipeline with Gemini Omni 1.1 Flash on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Gemini Omni 1.1 Flash pricing
Prepaid credits, no subscription. Each clip is charged at Gemini Omni 1.1 Flash's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Gemini Omni 1.1 Flash, answered
What does Gemini Omni 1.1 Flash cost?
OpenRouter lists about 3.4 cents a second at 360p, 10 cents at 720p and 30 cents at 4K, with audio always on. Our 3 second tests billed exactly 10 cents at 360p and 30 cents at 720p. On Treza it is charged from prepaid credits, and a failed generation costs nothing.
Can it start from my image?
Yes. It takes a first frame, a last frame or both. Describe what is in the image in your prompt: in our test the clip opened on the photo when the prompt matched it, and cut to a new scene when it did not.
Can I use Gemini Omni 1.1 Flash in chat?
Yes. Ask for Gemini Omni 1.1 Flash by name in Treza chat. On the canvas it is a model in the Video Generation node, and the pipeline it sits in can be published as an API endpoint.
How much does Gemini Omni 1.1 Flash cost on Treza?
Treza uses prepaid credits with no subscription. Each clip is charged at Gemini Omni 1.1 Flash's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Gemini Omni 1.1 Flash through an API?
Yes. Build a pipeline that uses Gemini Omni 1.1 Flash and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.