We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
google/gemini-omni-1.1-flashRuns on your balance at the prices above. New accounts start with free usage.
Settings
Google: Gemini Omni 1.1 Flash is a native multimodal video generation and editing model from Google. It is the generally available successor to Gemini Omni Flash Preview, and it sits in the video category while also covering text. If you have been tracking Google's Omni line, this is the version intended for production use rather than preview experimentation.
The model accepts text, image and video as input, and it produces text and video as output. Its context window is 131,072 tokens, with a maximum output of 65,536 tokens. On the video side it supports resolutions of 360p, 720p, 1080p and 4K, aspect ratios of 16:9 and 9:16, and clip durations of 3 through 10 seconds in single second steps. It can take a first frame, a last frame, or both, which makes controlled transitions and interpolation possible, and it can generate audio alongside the video.
Those capabilities point to a fairly specific set of workflows. Text-to-video covers concept shots, storyboards and short social clips, while image-to-video lets you animate a still or a product render. Supplying a first and last frame is useful when you need a defined start and end state, for example in advertising cutdowns or scene transitions. The 9:16 ratio and short durations suit vertical formats, and 4K output is there when the final deliverable needs the extra resolution. Because the model also reads video as input, editing and restyling existing footage is part of the same surface rather than a separate pipeline.
You call it through api14's OpenAI-compatible API using the model id "google/gemini-omni-1.1-flash". The supported request parameters are include_reasoning, max_tokens, reasoning, reasoning_effort, seed, temperature and top_p. The seed parameter is worth setting when you want reproducible generations across runs, and temperature and top_p give you the usual control over sampling. The reasoning parameters let you decide whether reasoning is included and how much effort is spent on it, which matters when a prompt needs planning before the video is produced.
There is no stated restriction that would rule the model out for general video work, but the fixed set of aspect ratios, 16:9 and 9:16, means formats outside those two are not covered here. Durations are capped at 10 seconds per generation, so longer sequences have to be built from multiple clips. If your task is purely text generation with no video component, a text-focused model will usually be the simpler choice.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
// Video generation is asynchronous: submit, then poll until completed.
let job = await client.post("/videos", { body: {
"model": "google/gemini-omni-1.1-flash",
"prompt": "A drone shot over turquoise ocean waves at sunrise",
"duration": 8,
"resolution": "720p",
"aspect_ratio": "16:9"
} });
while (!["completed", "failed"].includes(job.status)) {
await new Promise((r) => setTimeout(r, 5000));
job = await client.get(`/videos/${job.id}`);
}
console.log(job.status, job.unsigned_urls);
include_reasoningmax_tokensreasoningreasoning_effortseedtemperaturetop_pThis community has no topics yet. Open the first one about Google: Gemini Omni 1.1 Flash.