Image to video
Elo with audio · image-to-video arena
Veo 3.1 overview
Veo 3.1 by Google
The model produces fully synchronized audiovisual content, with support for various aspect ratios and high-definition output.
Veo 3.1 specs
- Model ID
google/veo-3.1-i2v- Developer
- Input
- Text
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Veo 3.1 API Overview
Veo 3.1 delivers professional-grade video quality through an improved diffusion-based architecture coupled with transformer-enhanced temporal modeling. It understands natural language prompts with high semantic accuracy and can replicate complex camera movements, lighting dynamics, and physical interactions.
Key Upgrades
- Richer native audio with realistic dialogue, ambient soundscapes, and precise sound effects guided directly from the text prompt.
- Improved cinematic control through stronger adherence to style, camera language, composition, and detailed visual direction.
- Enhanced image‑to‑video quality with better prompt alignment, higher visual fidelity, and consistent characters across scenes.
Core Video Generation Capabilities
Veo 3.1 API offers four primary modes of video generation, each designed to serve a distinct creative need.
Veo 3.1 Text-to-Video
Text-to-Video transforms detailed textual descriptions into complete 8-second clips, capturing subjects, environments, motion dynamics, cinematic techniques, and synchronized audio natively.The process ensures lifelike physics, temporal consistency, and immersive soundscapes, making it the foundation for standalone video creation without visual inputs.This workflow powers rapid ideation for advertising, social content, and narrative prototypes demanding full-scene autonomy from description alone.
Veo 3.1 Image-to-Video
Image-to-Video animates a single source image as the initial frame, evolving it into fluid motion sequences that honor the original composition, aesthetics, and focal elements.Dynamic extensions integrate realistic environmental interactions and ambient audio, preserving structural fidelity throughout the clip.Professionals rely on it to vitalize static designs, product visuals, or generated artwork, bridging still imagery to compelling motion narratives.
Veo 3.1 Reference-to-Video
Reference-to-Video anchors 1-3 source images to enforce unwavering consistency in character identity, attire, objects, or stylistic motifs across every frame of the output.The model sustains precise visual traits amid complex actions and scene changes, delivering production-ready clips at resolutions up to 4K.It excels in scenarios requiring brand-aligned characters, serialized storytelling, or customized avatars with uncompromised subject integrity.
Use cases
- Cinematic storytelling and marketing videos requiring realistic characters and natural audio.
- Social media content creation for platforms like TikTok and Instagram using portrait mode.
- Product demonstrations and tutorials with consistent visual branding.
- Animated shorts or scenes requiring smooth transitions and lip-synced dialogue.
Veo 3.1 benchmarks by 
Artificial Analysis
Human-preference results for Veo 3.1 in image to video and silent image to video, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Silent image to video
Elo · silent image-to-video arena
Models on AI/ML API
Arena results for models you can call with the same API key.
Image to video
Blind votes on clips with sound animated from a start image. Veo 3.1 ranks #21 of 29.
Silent image to video
Clips animated from a start image, judged as silent video. Veo 3.1 ranks #22 of 34.
Veo 3.1 API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.2 | per second |
| Additional | $0.52 | per /sec |
The final price depends on request parameters such as resolution or duration.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Veo 3.1 vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Veo 3.1 | $0.2 |
| Veo 3.1 Lite | $0.03 |
| Veo 3.1 Lite Generate Preview | $0.03 |
| Veo 3.1 Fast | $0.08 |
| Gemini Omni 1.1 Flash | $0.1014 |
How to use the Veo 3.1 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/veo-3.1-i2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/veo-3.1-i2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "google/veo-3.1-i2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to Veo 3.1
Related articles
Veo 3.1 FAQ
What inputs and outputs does Veo 3.1 support?
Veo 3.1 takes image, text as input and returns video.
How much does Veo 3.1 cost?
Veo 3.1 costs $0.2 per second on AI/ML API, billed as you go with no subscription.
How is Veo 3.1 billed?
Veo 3.1 costs $0.2 per second on AI/ML API, billed as you go with no subscription.
Can Veo 3.1 take an existing image as input?
Yes, Veo 3.1 accepts image input as well as a text prompt.
Who created Veo 3.1?
Veo 3.1 was built by Google.
How do I call Veo 3.1 on AI/ML API?
Send a request to v2/video/generations with google/veo-3.1-i2v as the model id.
Is Veo 3.1 available through a single API key?
Yes. Veo 3.1 is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is the Veo 3.1 model ID?
Use google/veo-3.1-i2v as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.