gemini-omni-1-2

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-1-2",
    "prompt": "A glass marble rolls fast along a wooden chain-reaction track through a sunlit workshop, one continuous smooth tracking shot. No text, no logos.",
    "resolution": "720p",
    "duration": 8,
    "aspect_ratio": "16:9"
  }'

import requests

response = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "gemini-omni-1-2",
        "prompt": "A glass marble rolls fast along a wooden chain-reaction track through a sunlit workshop, one continuous smooth tracking shot. No text, no logos.",
        "resolution": "720p",
        "duration": 8,
        "aspect_ratio": "16:9",
    },
    timeout=60,
)
response.raise_for_status()
task_id = response.json()["id"]

const response = await fetch('https://reapi.ai/api/v1/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gemini-omni-1-2',
    prompt:
      'A glass marble rolls fast along a wooden chain-reaction track through a sunlit workshop, one continuous smooth tracking shot. No text, no logos.',
    resolution: '720p',
    duration: 8,
    aspect_ratio: '16:9',
  }),
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
const { id: taskId } = await response.json();

package main

import (
    "encoding/json"
    "fmt"
    "net/http"
    "strings"
    "time"
)

func main() {
    body := strings.NewReader(`{
      "model": "gemini-omni-1-2",
      "prompt": "A glass marble rolls fast along a wooden chain-reaction track through a sunlit workshop, one continuous smooth tracking shot. No text, no logos.",
      "resolution": "720p",
      "duration": 8,
      "aspect_ratio": "16:9"
    }`)
    req, err := http.NewRequest("POST", "https://reapi.ai/api/v1/videos/generations", body)
    if err != nil { panic(err) }
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")
    client := &http.Client{Timeout: 60 * time.Second}
    res, err := client.Do(req)
    if err != nil { panic(err) }
    defer res.Body.Close()
    var task struct { ID string `json:"id"` }
    if err := json.NewDecoder(res.Body).Decode(&task); err != nil { panic(err) }
    fmt.Println(task.ID)
}

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/videos/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns a task id right away; poll the task endpoint until status is completed or failed. Polling does not consume credits.

Request body

Every clip comes with sound; there is no sound switch. There is no negative_prompt, seed or audio input. Unknown fields are refused rather than ignored.

Checked by reAPI before anything is charged:

• every media field is a public HTTP(S) URL — base64 and data: URIs are rejected
• resolution is one of the four values, and duration is a positive whole number
• the video to edit or extend can be measured (its length sets the bill — see Pricing)
• extend_from_task_id names a completed gemini-omni-1-2 task of yours

Every other rule on this page — image counts, frame combinations, mode limits, source length — is checked by the model when the task starts. A request that breaks one ends as a failed task with code 80007 and the exact reason, and is refunded in full.

Modes

A video input edits unless you ask for extend; with a video, reference, text_to_video, image_to_video and reference_to_video are refused. Google's guide documents up to 6 subject reference images (up to 3 per character, for up to 2 characters).

First and last frame

{
  "model": "gemini-omni-1-2",
  "prompt": "Smooth transition, the camera slowly pushes in.",
  "first_frame_image": "https://example.com/start.jpg",
  "last_frame_image": "https://example.com/end.jpg",
  "duration": 8
}

Edit

{
  "model": "gemini-omni-1-2",
  "prompt": "Make the violin invisible. Keep everything else the same.",
  "video_urls": ["https://example.com/clip.mp4"]
}

The edit keeps the source length; duration has no effect. Short, specific instructions work best; for a local change add "Keep everything else the same".

Extend an earlier task

{
  "model": "gemini-omni-1-2",
  "prompt": "The camera keeps panning across the mountains.",
  "extend_from_task_id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "omni_reference_task_type": "extend",
  "duration": 8
}

The result contains the original followed by the new part. Only your own completed gemini-omni-1-2 tasks can be named, and a task created from the website playground can be named only from the playground. To extend your own clip, send it in video_urls instead.

Troubleshooting

Response envelope

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "gemini-omni-1-2",
  "status": "completed",
  "created_at": 1789689600,
  "output": {
    "video_urls": ["https://.../0.mp4"]
  },
  "error": null
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed", then read output.video_urls. A failed task carries error.code and error.message; see the errors catalog. Every video carries Google's invisible SynthID watermark.

Pricing

Gemini Omni 1.2 bills per second, at a rate set by the resolution:

credits = ceil(per_second_rate × billable_seconds × 1000)     1 credit = $0.001

source is the input video's picture length, measured by reAPI when the request is accepted and rounded up to whole seconds; the eighth covers reading the input video. At any resolution, editing a 6.2-second clip bills 7 + 7/8 = 7.875 seconds, and extending an 8-second clip by 4 seconds bills 4 + 1 = 5 seconds. Failed tasks are refunded in full.

Live per-second rates for each resolution are on the model page.

Tips

• Describe subject, place, camera move, light and sound; the clip's audio follows the prompt.
• The model likes to cut between shots; ask for "a single continuous shot" when you need one.
• Draft at 360p, then render the shot you keep at 1080p or 4k with the same request.
• For an edit, change one thing at a time and say what must stay the same.
• English prompts are fully supported; other languages are not evaluated by Google.

Related

• Gemini Omni 1.2 playground and pricing
• Gemini Omni 1.1
• Veo 3.1
• Errors catalog
• Authentication
• Quickstart