Gemini Omni Flash

Name: Gemini Omni Flash
Author: Google

google/gemini-omni-flash

Gemini Omni Flash is Google's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.

Use in agent Get API key

Base price: $0.13USD / run
Execution: async
Model type: video
Input fields: 3

Try the model

Playground

Open playground

Input

Prompt(string)

The text prompt describing the video you want to generate.

Aspect Ratio(string)

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.

Duration(integer)

310

The duration of the generated video, in seconds. Range: 3 to 10.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.13 / run
Billing formula: Math.ceil(params.prompt.length / 1000) * 0.021875

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
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Gemini Omni Flash

google/gemini-omni-flash creates a new video from written scene direction, jointly reasoning about visuals, motion, camera behavior, dialogue, ambience, and sound. Gemini Omni Flash combines multimodal understanding with video generation, supporting coherent scenes, real-world physical behavior, character continuity, and synchronized audio in one creative process. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.

For production work, the text-to-video workflow is intended for rapid conversational iteration, allowing the creative brief to refine action, composition, sound, and narrative intent instead of rebuilding the asset through separate tools. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.

Highlights

Prompt-built video scenes. Converts written direction into a complete moving shot without requiring a starting image, making the base route useful for storyboards and motion concepts that begin as language.

Cinematic action interpretation. Resolves subjects, setting, action, atmosphere, and camera intent together so the generated sequence follows a unified creative brief.

Native temporal construction. Builds motion and scene progression across the clip rather than applying a simple animated effect to a supplied still.

Fast concept exploration. The Flash-oriented model supports rapid comparison of different shot ideas before teams commit to a more expensive finishing workflow.

Pricing

Prompt allowance	Price
Each started 1,000 prompt characters	$0.021875

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "aspect_ratio": "21:9",
  "duration": 8,
  "prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam slowly sweeping across the dark sea."
}

Technical Specs

Spec	Value
Model ID	`google/gemini-omni-flash`
Inputs	aspect_ratio, duration, prompt
Required inputs	prompt
Output fields	content_type, url
Execution	Async (submit, then poll for result)
Aspect Ratio	21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16

Related Models

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

# 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 $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "google/gemini-omni-flash",
  "prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam slowly sweeping across the dark sea.",
  "duration": 8
}
SANDBASE_JSON
)
run_id=$(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

Model	Context	Input / 1M	Output / 1M	Released
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