Start building

Gemini Omni Flash

google/gemini-omni-flash/reference-to-video

Gemini Omni Flash by Google - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.

Use in agentGet API key
Base price
$0.13USD / run
Execution
async
Model type
video
Input fields
4

Try the model

Playground

Open playground
Input
The text prompt describing the video. You can bind reference images to roles inline using tags like ``<IMAGE_REF_0>`` (see the Omni Flash prompt guide).

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

URLs of the reference images to incorporate into the video.
310
The duration of the generated video, in seconds. Range: 3 to 10.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.13 / run
Billing formula
params.duration * 0.13

Context & modalities

Input
Schema-defined
Output
video

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Google
Model ID
google/gemini-omni-flash/reference-to-video
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Gemini Omni Flash Reference to Video

Gemini Omni Flash Reference to Video generates a video under the guidance of reference imagery and a required written brief. Unlike the single-image animation variant, its images field accepts a collection of visual references that can be incorporated into the requested scene.

Reference roles can be bound inside the prompt with tags such as <IMAGE_REF_0>, making the connection between written direction and supplied material explicit. The endpoint also offers ten aspect ratios and a three-to-ten-second duration range for shaping the final delivery.

Highlights

  • Multiple visual references in one request. Provide an array of image URLs when a video should draw on more than one piece of source material.
  • Inline reference binding. Use tags such as <IMAGE_REF_0> in the prompt to assign supplied images to specific roles in the video brief.
  • Reference-guided generation. The Gemini Omni Flash catalog explicitly documents reference media as guidance for video generation.
  • Delivery controls for different placements. Ten aspect ratios and a duration range of three to ten seconds cover broad framing and timing needs.

Pricing

  • Local price formula: params.duration * 0.13

Technical Specs

  • Model ID: google/gemini-omni-flash/reference-to-video
  • Request fields: aspect_ratio (string, optional, enum: 21:9/16:9/3:2/4:3/5:4/1:1/4:5/3:4 (10 values total)); duration (integer, optional, min 3, max 10); images (array, optional); prompt (string, required)
  • Required fields: prompt
  • Output fields: content_type (string, optional); url (string, required)
  • Execution mode: async

When to Use

  • Use this variant when several reference images need to inform the people, objects, styling, or other roles described in a video prompt.
  • Choose it when reference-guided generation also needs a defined duration and aspect ratio for the target channel.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
google/gemini-omni-flash/reference-to-video
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "google/gemini-omni-flash/reference-to-video",
  "images": [
    "https://static.sandbase.ai/examples/google/gemini-omni-flash/reference-to-video/input_images_0.png",
    "https://static.sandbase.ai/examples/google/gemini-omni-flash/reference-to-video/input_images_1.png"
  ],
  "prompt": "A cat playfully batting at a ball of yarn in a sunlit living room.",
  "duration": 8
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Gemini Omni FlashThis model
Google		———Jun 30, 2026
Gemini Omni Flash
Google		———Jun 30, 2026
Gemini Omni Flash
Google		———Jun 30, 2026
Gemini Omni Flash
Google		———Jun 30, 2026
Veo 3.1 Fast
Google		———May 11, 2026
Veo3.1 Lite FLF
Google		———Mar 31, 2026