Skip to content
Google logo

Gemini Omni Flash

Text-to-Video • Google

View as MarkdownAgent setup

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

  • Third-party

Preview high-performance multimodal video generation and editing model with conversational controls and generated audio.

Model Info
Terms and Licenselink ↗
Pricing
  • Input text (per 1M tokens)$1.50
  • Input image (per 1M tokens)$1.50
  • Input audio (per 1M tokens)$1.50
  • Input video (per 1M tokens)$1.50
  • Output text (per 1M tokens)$9.00
  • Reasoning (per 1M tokens)$9.00
  • Output video (per 1M tokens)$17.50

Usage

const response = await env.AI.run(
  'google/gemini-omni-flash',
  {
    text: 'A school of silver fish moving through a sunlit coral reef, slow cinematic tracking shot with drifting particles.',
    aspect_ratio: '16:9',
    resolution: '720p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "google/gemini-omni-flash",
  "input": {
    "text": "A school of silver fish moving through a sunlit coral reef, slow cinematic tracking shot with drifting particles.",
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/google/gemini-omni-flash/underwater-reef.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Examples

Breakfast robot — Generate a portrait-format character scene
const response = await env.AI.run(
  'google/gemini-omni-flash',
  {
    text: 'A friendly home robot preparing breakfast in a bright modern kitchen, gentle handheld camera movement.',
    aspect_ratio: '9:16',
    resolution: '720p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "google/gemini-omni-flash",
  "input": {
    "text": "A friendly home robot preparing breakfast in a bright modern kitchen, gentle handheld camera movement.",
    "aspect_ratio": "9:16",
    "resolution": "720p"
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/google/gemini-omni-flash/breakfast-robot.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}
Desert train — Generate a high-resolution desert scene
const response = await env.AI.run(
  'google/gemini-omni-flash',
  {
    text: 'A vintage train crossing a vast desert at golden hour, dust glowing in the sunset as the camera sweeps alongside.',
    aspect_ratio: '16:9',
    resolution: '1080p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "google/gemini-omni-flash",
  "input": {
    "text": "A vintage train crossing a vast desert at golden hour, dust glowing in the sunset as the camera sweeps alongside.",
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/google/gemini-omni-flash/desert-train.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}
Northern lights — Generate a low-resolution night landscape
const response = await env.AI.run(
  'google/gemini-omni-flash',
  {
    text: 'Colorful northern lights dancing above a frozen lake, a small cabin glowing warmly in the foreground.',
    aspect_ratio: '16:9',
    resolution: '360p',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "google/gemini-omni-flash",
  "input": {
    "text": "Colorful northern lights dancing above a frozen lake, a small cabin glowing warmly in the foreground.",
    "aspect_ratio": "16:9",
    "resolution": "360p"
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/google/gemini-omni-flash/northern-lights.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

text
stringText prompt or editing instruction
image
stringFirst-frame or primary reference image
last_frame
stringLast-frame reference image
video
stringReference video for editing or extension
audio
stringReference audio input
previous_interaction_id
string
aspect_ratio
stringenum: 16:9, 9:16
resolution
stringenum: 360p, 720p, 1080p, 4k

API Schemas (Raw)

Input
Output

Was this helpful?