What input formats are supported?

Supported input formats include MP4, MOV, WebM, M4V, and GIF. You can provide input via file upload or URL.

How long can the extended video be?

You can extend a video by any length. The service is charged per second of generated content.

What is the model type behind Veo 3.1 Extend?

It uses a proprietary diffusion-based video generative model.

How does it handle audio?

Audio continuation is optional and can be synchronized with the extended video.

What is the API pricing for Veo 3.1 Extend Video?

Generation costs $0.21 per second with audio off and $0.42 per second with audio on.

What are the key features of Veo 3.1 Extend Video?

Key features include seamless motion continuation for fluid scene extension, style-consistent storytelling that preserves the original's look, and high-fidelity visual quality matching Veo 3.1's cinematic output.

What are the primary use cases for Veo 3.1 Extend Video?

It is best used for content lengthening for social media platforms, story continuation for episodic scenes, extending advertising and marketing videos, and creating longer educational or explainer videos.

How does Veo 3.1 Extend differ from Veo 3.1 Fast Extend?

The standard Extend is optimized for maximum cinematic quality and is preferable for hero shots. Fast Extend is designed for high-volume social media workflows and rapid experimentation.

How does Veo 3.1 Extend complement the standard Veo 3.1 model?

Extend is optimized for continuity and merging segments into a single file, while Veo 3.1 focuses on initial scene creation. They are complementary stages in a content creation pipeline.

Veo 3.1 Extend Video — API Pricing and Benchmarks

Name: Veo 3.1 Extend Video API
Brand: Google

Overview

What Is Veo 3.1 Extend Video

Veo 3.1 Extend Video lets you feed a previously generated Veo 3.1 clip and generate an additional segment that is automatically merged into one continuous MP4 file. The extension follows the last frames, motion, and style of the original, while allowing you to redirect the narrative via a fresh text prompt describing what should happen next.

Technical Specifications

Input Format Support: MP4, MOV, WebM, M4V, GIF
Input Method: File upload, URL
Output Duration: Extendable by any length (charged per second)
Model Type: Proprietary diffusion-based video generative model
Temporal Consistency: Advanced motion propagation and latent interpolation
Audio Handling: Optional synchronized audio continuation

Performance Characteristics and Benchmarks

Quality: Near-cinematic output resolution and motion smoothness.
Coherence: Maintains object persistence, scene geometry, and lighting continuity over extended frames.
Latency: Cloud-optimized inference; generation time scales linearly with output duration.

API Pricing

$0.26 / sec (audio off)
$0.52 / sec (audio on)

Key Features

Veo 3.1 Extend Video focuses on natural continuation rather than arbitrary editing; its strength is seamless extension of Veo‑native content

Seamless motion continuation

Extends motion trajectories, camera movement, and scene dynamics from the last frames of the original clip, reducing visible cuts or jumps.
Designed for cinematic continuity, so the extended segment feels like one continuous shot rather than a stitched montage.

Style‑consistent storytelling

Preserves the visual style, color grading, and composition of the source Veo clip unless the prompt explicitly requests a transition.
Allows prompts to specify whether to maintain or gradually shift style, mood, and ambiance over the extension.

High‑fidelity visual quality

Uses the same core Veo 3.1 rendering capabilities, supporting realistic lighting, textures, and cinematic camera paths at 720p or 1080p.
Works across different genres (live‑action‑style, animation, stylized scenes) as long as the input clip is compatible with Veo’s safety filters.

Primary Use Cases

Veo 3.1 Extend Video is best used when you already have a strong base clip and want to expand the narrative, add beats, or create platform‑ready longer cuts.

Content lengthening for social platforms

Turn 4–8 second Veo previews into 10–30+ second clips for Shorts, Reels, TikTok, and Stories by chaining multiple extensions.
Maintain the same characters, setting, and style while evolving action or dialogue across segments.

Story continuation and episodic scenes

Extend a key moment (e.g., a character reveal or establishing shot) into a full micro‑sequence by adding follow‑up actions and camera moves.
Build episodic arcs by iteratively extending scenes in pre‑visualization, animatics, or concept trailers.

Advertising and marketing

Start with a short hero shot and extend into product reveals, call‑to‑action shots, or branded outros without cutting away.
A/B test different endings by generating multiple alternative extensions from the same base clip and swapping them in.

Educational and explainer videos

Take a concise visual demonstration and extend it with additional steps, alternative angles, or zoom‑in shots for clarity.
Build longer educational loops by repeating extend calls while preserving consistent visual identity.

Comparison with Other Models

vs Veo 3.1 Fast Extend: Standard Extend aims for maximum cinematic quality and may be preferable for hero shots, while Fast Extend suits high‑volume social workflows and rapid experimentation.

vs Veo 3.1: Extend is optimized for continuity and single‑file merging, while Veo focuses on initial scene creation, making them complementary stages in a content pipeli

‍

Use cases

Extending a Veo-generated video is documented as suitable for continuing a story or action from the last second of a previous clip while keeping visual and audio consistency.

It is documented for creating longer, seamless shots from an existing clip, including establishing shots that continue the action from the original video.

It is documented for adding a short continuation to a previously generated video, producing a single merged clip with the extended segment.

It is also documented for quality-focused postproduction workflows where a raw clip can be extended into a more polished final sequence.

How to use Veo 3.1 Extend Video API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to veo3.1/extend-video.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/video/generations",
    headers=headers,
    json={
      "model": "veo3.1/extend-video",
      "prompt": "A serene timelapse of clouds over a mountain range"
    },
).json()
gid = job["id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error"):
        break
    time.sleep(5)
print(res["video"]["url"])

const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "veo3.1/extend-video",
    "prompt": "A serene timelapse of clouds over a mountain range"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 5000));
  res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (!["completed", "error"].includes(res.status));
console.log(res.video.url);

# submit the generation — the response contains the job "id"
curl -X POST https://api.aimlapi.com/v2/video/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"veo3.1/extend-video","prompt":"A serene timelapse of clouds over a mountain range"}'

# then poll until status is "completed" — video.url holds the result
curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.