Gemini Omni 1.2 Flash API: Video from $0.10

export LAOZHANG_API_KEY="your LaoZhang API key"
export BASE_URL="https://api.laozhang.ai"

curl -s -X POST "$BASE_URL/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "A street musician plays the violin under a street lamp on a rain-soaked cobblestone street at dusk. The camera slowly pushes in. She stops, smiles at the camera and says: \"This one is for you.\" Soft rain and violin in the background.",
    "resolution": "720p",
    "seconds": "10",
    "aspect_ratio": "16:9"
  }' | tee omni-create.json

export VIDEO_ID=$(jq -r '.id' omni-create.json)

{
  "id": "task_pmz6yURlFEdpV7oQREUQWFMvYe0ZNN0j",
  "object": "video",
  "model": "gemini-omni-1.2-flash",
  "status": "queued",
  "progress": 0,
  "resolution": "720p",
  "seconds": "10",
  "created_at": 1794395489
}

curl -s -X POST "$BASE_URL/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "The robot chef stirs the soup in the pot, raises a whisk and says cheerfully: \"Dinner is almost ready!\" The camera slowly pushes in as steam rises from the pot.",
    "resolution": "720p",
    "seconds": "6",
    "image": "https://example.com/robot-chef.jpg"
  }'

curl -s -X POST "$BASE_URL/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F model=gemini-omni-1.2-flash \
  -F prompt="Waves break on the rocks below the lighthouse, clouds drift slowly, and the lighthouse beam comes on" \
  -F resolution=360p \
  -F seconds=5 \
  -F input_reference=@./lighthouse.jpg

curl -s -X POST "$BASE_URL/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "The robot chef from image 2 walks into the ramen shop from image 1 and sits down at the counter. The cat sleeping next to it wakes up.",
    "resolution": "720p",
    "seconds": "8",
    "reference_images": [
      "https://example.com/ramen-shop.jpg",
      "https://example.com/robot-chef.jpg"
    ]
  }'

curl -s -X POST "$BASE_URL/v1/videos" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "gemini-omni-1.2-flash",
    "prompt": "A cyclist rides through a coastal town from morning to sunset: market, harbor, cliff road, lighthouse",
    "size": "1080x1920",
    "seconds": "10"
  }'

curl -s "$BASE_URL/v1/videos/$VIDEO_ID" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY"

{
  "id": "task_cpg5YjZdGpf5G64hpcehVFip3yEzBGmJ",
  "object": "video",
  "model": "gemini-omni-1.2-flash",
  "status": "in_progress",
  "progress": 24,
  "resolution": "360p",
  "seconds": "3",
  "size": "640x360",
  "created_at": 1794395880
}

{
  "id": "task_cpg5YjZdGpf5G64hpcehVFip3yEzBGmJ",
  "object": "video",
  "model": "gemini-omni-1.2-flash",
  "status": "completed",
  "progress": 100,
  "resolution": "360p",
  "seconds": "3",
  "size": "640x360",
  "created_at": 1794395880,
  "completed_at": 1794395908,
  "video_url": "https://media.laozhang.ai/videos/omni-video_b1c75730eec94afecd7a03e6-8a6288ae03f4.mp4"
}

{
  "id": "task_bgrPGFRI5wEwlOW0XrCy5b29xTGHlKbt",
  "object": "video",
  "model": "gemini-omni-1.2-flash",
  "status": "failed",
  "progress": 100,
  "resolution": "360p",
  "seconds": "3",
  "size": "640x360",
  "created_at": 1794395882,
  "error": {
    "code": "video_generation_failed",
    "message": "input_reference must be a public internet link. This request is not charged."
  }
}

curl -L -o omni-video.mp4 "$(curl -s "$BASE_URL/v1/videos/$VIDEO_ID" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" | jq -r '.video_url')"

import os
import time

import requests

BASE_URL = "https://api.laozhang.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['LAOZHANG_API_KEY']}"}

task = requests.post(
    f"{BASE_URL}/v1/videos",
    headers=HEADERS,
    json={
        "model": "gemini-omni-1.2-flash",
        "prompt": "A street musician plays the violin under a street lamp on a rain-soaked cobblestone street at dusk. The camera slowly pushes in. She stops, smiles at the camera and says: \"This one is for you.\" Soft rain and violin in the background.",
        "resolution": "720p",
        "seconds": "10",
        "aspect_ratio": "16:9",
    },
    timeout=120,
)
task.raise_for_status()
video_id = task.json()["id"]

deadline = time.time() + 15 * 60
while True:
    video = requests.get(f"{BASE_URL}/v1/videos/{video_id}", headers=HEADERS, timeout=60).json()
    if video["status"] == "completed":
        break
    if video["status"] == "failed":
        raise RuntimeError(video["error"]["message"])
    if time.time() > deadline:
        raise TimeoutError(f"{video_id} is still running; keep polling the same id later")
    time.sleep(5)

with open("omni-video.mp4", "wb") as f:
    f.write(requests.get(video["video_url"], timeout=300).content)
print("Saved omni-video.mp4,", video["size"], video["seconds"], "seconds")