Gemini Omni 1.2 Flash API: 15-Second Video, Price per Second, Model ID and How to Call It

Short answer

Google made Gemini Omni 1.2 Flash generally available on November 5, 2026 (Gemini API release notes), and TeamoRouter supports it. It's Google's model for generating and editing video. The model ID is gemini-omni-1.2-flash.

• What's new compared with 1.1: clips up to 15 seconds (1.1: 10), native audio, better character consistency across up to 6 reference images, and conversational editing: interpolate between a first and last frame (3–10 s) or extend a clip by 3–10 s per turn, up to 30 s in total.
• Output: 3–15 s at 360p, 720p, 1080p or 4K, 24 FPS.
• Google's price (paid tier only): $1.50 per 1M input tokens. Video output is $12.00 per 1M tokens, 30% less than 1.1's $17.50. Google counts 5,792 tokens per second of 720p video, which is about $0.07 per second: roughly $0.70 for a 10-second clip and $1.04 for 15 seconds.
• On TeamoRouter: create jobs with the OpenAI-compatible /v1/videos API. The same key also calls Claude, GPT and Gemini text models, and you pay per job from a $5 balance.

New accounts start with a $0 balance — top up before your first request. Top up from $5. If a request returns 402 (400 on the OpenAI format) with "wallet balance is insufficient", your balance is empty — your base URL and key are fine. Top up and retry.

Get a key and generate video with Gemini Omni 1.2 Flash

What changed from Gemini Omni 1.1 Flash

From Google's model page and pricing page:

Google also doubled the paid-tier rate limits. From December 3, 2026, requests to gemini-omni-1.1-flash will be routed to gemini-omni-1.2-flash automatically and billed at 1.2 rates.

How much a clip costs

Google bills video by output tokens. Its pricing page gives the token rate per second for each resolution:

The prompt and any reference images are input, billed at $1.50 per 1M tokens. Gemini Omni 1.2 Flash has no free tier. TeamoRouter's current price is on the video models page and the pricing page.

Call it through TeamoRouter

Python with the OpenAI SDK:

import os, time
from openai import OpenAI

client = OpenAI(api_key=os.environ["TEAMO_API_KEY"], base_url="https://api.teamorouter.com/v1")
video = client.videos.create(
    model="gemini-omni-1.2-flash",
    prompt="A paper boat drifting down a rainy city street at night, neon reflections, sound of rain",
    seconds="8",
    size="1280x720",
)
while video.status in ("queued", "in_progress"):
    time.sleep(5)
    video = client.videos.retrieve(video.id)
if video.status == "failed":
    raise RuntimeError(video.error)
client.videos.download_content(video.id).write_to_file("omni.mp4")

• For image-to-video, add input_reference={"image_url": "https://..."}.
• GET /v1/models?type=video lists the model ID for each mode and the durations and sizes it accepts. Full reference: video generation API.
• Conversational editing and extension are part of Google's Interactions API. TeamoRouter's /v1/videos covers text-to-video and image-to-video jobs.
• Prefer a UI? Use the video workbench with the same balance.

FAQ

Is Gemini Omni 1.2 Flash free?

No. Google lists it only on the paid tier of the Gemini API. On TeamoRouter you pay per job from a prepaid balance, from $5.

How long can a video be?

3 to 15 seconds per generation. With Google's per-turn extension you can grow a clip by 3–10 seconds at a time, up to 30 seconds in total.

What happens to gemini-omni-1.1-flash?

It still works. From December 3, 2026, Google routes its requests to gemini-omni-1.2-flash and bills them at 1.2 rates.

Do I need a Google account?

Not through TeamoRouter: you use a TeamoRouter key and balance. Details: using Gemini Omni 1.2 Flash without Google billing.

Related

• Use Gemini Omni 1.2 Flash without a Google billing account
• Gemini Omni 1.2 Flash vs Seedance 2.5 vs MiniMax H3
• Video generation API
• All video models