Gemini Omni 1.1 Flash is the generally available release of Google's multimodal video model, covering text-to-video, image-to-video, reference-to-video, and video editing in one API. Point it at a text prompt, a reference image, or an existing clip, and get back a short video — with conversational multi-turn edits available through the Gemini Interactions API. The 1.1 release adds scene extension (continuing an existing clip up to 40 seconds total), start/end frame control for guided transitions, and a cheaper 360p draft mode that upscales to 1080p or 4K.
Describe a scene and receive a short video clip — for social content, marketing materials, or product demos where written briefs need to become motion assets.
Animate a still image into a video sequence. Useful for product photography, character animation, and giving motion to static visuals.
Bind reference images to specific roles in the prompt using tags like <IMAGE_REF_0> for precise control over character appearance, environment, or style.
Pass an existing video clip and prompt the model to modify or extend it — background changes, motion adjustments, style transformation, or continuing a scene up to 40 seconds.
Gemini Omni 1.1 Flash: Versatile multi-task video model with scene extension and draft-to-final workflow. Best for workflows that need multiple generation modes in one API.
Seedance 2.0: ByteDance video model with up to 4K resolution. Choose Seedance for ultra-high-resolution output requirements.
Kling Video: Alternative video generation with distinct motion characteristics for different aesthetic needs.
Gemini Omni 1.1 Flash is documented as suited for fast, conversational video generation and editing, especially when turning text and images into video.
It is also suited for iteratively refining and editing videos through natural-language conversation, preserving the parts of the video that should remain unchanged.
A third documented use case is extending an existing video scene, continuing footage seamlessly from where it left off while maintaining visual consistency and narrative flow.
It is additionally suited for creating or updating videos with creative controls such as first-and-last-frame interpolation and resolution upscaling for polished outputs.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "google/gemini-omni-1.1-flash", "prompt": "A serene timelapse of clouds over a mountain range" }, ).json() gid = job["id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error"): break time.sleep(5) print(res["video"]["url"])
const headers = {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers,
body: JSON.stringify({
"model": "google/gemini-omni-1.1-flash",
"prompt": "A serene timelapse of clouds over a mountain range"
}),
})).json();
let res;
do {
await new Promise((r) => setTimeout(r, 5000));
res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (!["completed", "error"].includes(res.status));
console.log(res.video.url);
# submit the generation — the response contains the job "id" curl -X POST https://api.aimlapi.com/v2/video/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"google/gemini-omni-1.1-flash","prompt":"A serene timelapse of clouds over a mountain range"}' # then poll until status is "completed" — video.url holds the result curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
Billed per second of generated video at $0.131768/sec, regardless of output resolution.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemini Omni 1.1 Flash This page | Video generation | |||
| Video generation | ||||
| Cinematic video + native audio |
Gemini Omni 1.1 Flash takes image, text, video as input and returns video.
Gemini Omni 1.1 Flash became available on August 27, 2026.
Gemini Omni 1.1 Flash is priced at $11.7 / 1M tokens.
Gemini Omni 1.1 Flash is billed per generation — a fixed charge per output rather than by prompt length.
Yes, Gemini Omni 1.1 Flash accepts image input as well as a text prompt.
Gemini Omni 1.1 Flash was built by Google.
Send a request to https://api.aimlapi.com/v2/video/generations with google/gemini-omni-1.1-flash as the model id.
Yes. Gemini Omni 1.1 Flash is served through AI/ML API, so the same key and endpoint format used for other models applies.
-min.webp){kind=small}