Gemini Omni Flash Video Edit API
google/gemini-omni-flash/video-edit
Gemini Omni Flash Video Edit applies natural-language edit instructions to existing videos, enabling prompt-guided changes to scenes, style, motion, and visual details while preserving the original video context. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | Instruction describing how to edit the source video. |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/google/gemini-omni-flash/video-edit" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field"
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/google/gemini-omni-flash/video-edit",
headers=HEADERS,
json={
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field"
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/google/gemini-omni-flash/video-edit", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field"
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
Gemini Omni Flash Video Edit API
Prompt-based video editing that preserves scene context, with no cold starts and affordable short-form pricing.
Gemini Omni Flash Video Edit is a natural-language video editing model designed to transform existing videos using simple text instructions. It enables targeted changes to style, motion, scene appearance, and visual details while preserving the original video context, making it well suited for fast, production-friendly creative iteration.
🚀 Key Features
- Prompt-based video editing: Edit an existing video using a simple natural-language prompt instead of manual timeline-based workflows.
- Scene-aware transformation: Apply visual changes while maintaining scene coherence and overall structural consistency.
- Context-preserving edits: Ideal for modifying specific elements without unnecessarily changing the rest of the video.
- Minimal input workflow: Only two required inputs—source video and prompt—keep the editing process straightforward.
- No cold starts: Built for responsive production usage with consistent availability and reduced wait time.
- Affordable short-form generation: Per-second pricing makes it practical for social clips, ad creatives, and rapid experimentation.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model Name | Gemini Omni Flash Video Edit API |
| Model ID | google/gemini-omni-flash/video-edit |
| Task Type | image-to-video(existing video editing) |
| Model Architecture | Natural-language-guided video editing model |
| Input Format | Video URL + Prompt |
| Required Inputs | video: source video URL to edit; prompt: instruction describing the desired edit |
| Output Format | Video URL |
| Editing Capabilities | Scene refinement, visual restyling, lighting and mood changes, detail enhancement, presentation changes |
| Consistency Behavior | Preserves original scene context and coherence where possible |
| Duration Limits | Minimum 3 seconds, maximum 10 seconds |
| Frame Rate | Not publicly specified |
| Resolution | Not publicly specified |
| Latency | Fixed latency not disclosed; positioned for no cold starts and production-ready responsiveness |
| Best Fit | Short-form content, ad creatives, social media clips, iterative visual editing workflows |
Sample Prompts
Restyle the video with a cinematic nighttime look, stronger neon reflections, and keep the subject motion and framing unchanged.Change the scene to a warm sunset atmosphere with soft golden lighting. Keep everything else the same.Make the video look like a premium fashion commercial with richer contrast and cleaner textures while preserving the original scene structure.
💰 Pricing
| Source Video Duration | Price |
|---|---|
| 3s or less | $0.48 |
| 5s | $0.80 |
| 8s | $1.28 |
| 10s | $1.60 |
Pricing rule: $0.16 per second of source video duration, with a 3-second minimum and 10-second maximum.
💡 Best Use Cases
- Video restyling: Update the visual style, lighting, mood, or atmosphere of existing footage without reshooting.
- Scene refinement: Apply focused edits while preserving the original scene layout and subject relationships.
- Creative iteration: Test multiple edit directions from the same source video for faster review and experimentation.
- Short-form content production: Create polished clips for social media, advertising, and creative marketing workflows.
🔗 Related Models
- Google Gemini Omni Flash Text To Video: Better suited for generating entirely new videos from text prompts.
- Google Imagen3: Useful for high-quality image generation and visual concept development alongside video workflows.