Veo 3.1 API : Create AI Videos With Sound From Text or an Image
Try Veo 3.1 online right here: write a prompt or add a first frame, pick standard, fast or lite, and get a video of 4, 6 or 8 seconds with sound, up to 4K. Then call the same model from your product through the Veo 3.1 API, with one key and one balance.
- Three versions
- Videos with sound
- Billed by output length
- Open Veo 3.1 API
Features
Key Veo 3.1 API Capabilities
Text and image to video in one API
The Veo 3.1 API turns a prompt, or a first frame and a prompt, into a video through one endpoint, POST /v1/tasks. Switch between text_to_video and image_to_video with the mode parameter and keep the rest of your integration as it is.
Video and sound in one pass
Veo 3.1 generates the sound together with the picture, so a clip is ready to post without a separate audio step. standard and fast always include it; lite can turn it off with generate_audio, and the price per second stays the same.
Three versions, one integration
Choose the version per request with variant: standard for the best quality, fast for a lower price, and lite, the cheapest, at 720p. All three share one endpoint and task format, so you can use each one where it fits.
Up to 4K, landscape or portrait
standard and fast render at 720p, 1080p or 4K, and lite at 720p. Pick 16:9 for landscape or 9:16 for portrait, and set duration to 4, 6 or 8 seconds.
Short prompts, detailed shots
standard and fast expand your prompt into a detailed shot description before they generate, so even a one-line idea gets camera moves, light and action. lite follows your prompt as written. Prompts can run up to 8,000 characters; English works best.
First and last frame with lite
In image to video, your image becomes the first frame of the shot. lite can also take a last frame and generate the 8 seconds in between, and with aspect_ratio set to auto it follows the shape of your first frame.
Overview
What Is Veo 3.1?
- Model ID
veo-3.1- Versions
standard · fast · lite- Modes
- 2
- Length
- 4 / 6 / 8s
- Resolution
- 720p / 1080p / 4k
- Aspect ratio
- auto · 16:9 · 9:16
- Sound
- On by default, can be turned off
- Prompt
- Up to 8000 characters
- Price
- From $0.0585 / s
Veo 3.1 is an AI video model that creates the picture and the sound together. Give it a prompt, or a prompt and a first frame, and it returns an MP4 of 4, 6 or 8 seconds at 720p, 1080p or 4K, in 16:9 or 9:16, at 24 frames per second. Prompts can run up to 8,000 characters and work best in English, and the standard and fast versions turn a short prompt into a detailed shot description before generating.
On NanoAPI, Veo 3.1 is one model with two modes and three versions. text_to_video generates from a prompt alone, and image_to_video starts from a first frame. The variant parameter picks the version: standard for the best quality, fast for a lower price, and lite, the cheapest, which renders at 720p and is the only one that can add a last frame, follow the first frame's aspect ratio with auto or turn the sound off. Every request uses the model value veo-3.1 and sends variant, mode, prompt, resolution, aspect_ratio and duration.
Use Veo 3.1 online in the studio at the top of this page, then call the Veo 3.1 API at https://api.nanoapi.ai/v1 from your own app. Both draw on the same prepaid balance at the same per-second prices, a failed generation is never charged, and finished videos are kept for 15 days, so save the ones you want to keep.
Modes
Veo 3.1 Modes Compared
One endpoint, two modes: pick the one that matches what you start from. Both cost the same per second; the price depends only on the version and resolution.
| Mode | Input | Best for |
|---|---|---|
Text to Videotext_to_video | A prompt (required) | Concept shots, B-roll and scenes you only have in words |
Image to Videoimage_to_video | A first frame and a prompt; lite can add a last frame (8 s) | Animating a photo, product shot or artwork, or moving between a fixed start and end with lite |
Pricing
Veo 3.1 API Pricing
Priced per second of the video you ask for, by version and resolution: both modes cost the same, and sound never changes the price.
| Version | 720p / s | 1080p / s | 4k / s |
|---|---|---|---|
Standardstandard | $0.39 | $0.39 | $0.585 |
Fastfast | $0.156 | $0.156 | $0.351 |
Litelite | $0.0585 | — | — |
Live prices per second for each version. Cost = output length × price; sound on or off costs the same. Failed runs are fully refunded.
How it works
How to Use the Veo 3.1 API
- 1
Step 1: Get your API key
Sign in to NanoAPI with Google and create a key on the API Keys page of the console. The key authenticates every Veo 3.1 API request, so keep it on your server.
- 2
Step 2: Top up your balance
Add funds on the Top up page of the console, from $10. The balance is prepaid in USD, never expires and is shared by every NanoAPI model and the studio above, so you can test prompts before you write code.
- 3
Step 3: Create a Veo 3.1 video
Send POST /v1/tasks with model veo-3.1, a variant (standard, fast or lite), a mode, your prompt, resolution, aspect_ratio and duration, plus image_urls for image to video. The task is queued in under a second, and its cost is reserved within a few seconds.
- 4
Step 4: Get the result
Receive the finished task at your webhook_url or poll GET /v1/tasks/{task_id}. A Veo 3.1 video usually takes 1 to 2 minutes and comes back as a public MP4 URL with sound, plus a silent, compressed preview.
Why NanoAPI
Why Use the Veo 3.1 API on NanoAPI
One API for every model
The Veo 3.1 API uses the same POST /v1/tasks endpoint, task object and webhooks as every NanoAPI model, so a new version, mode or model never means a new integration.
Pay per second of output
The cost is duration × the price per second of the version and resolution, known before you submit. No subscription: top up from $10, and the balance never expires.
Sound costs nothing extra
Every second costs the same with or without sound, and both modes share one price. You pay for the seconds of video you ask for and nothing on top.
Failed runs are free
Each task reserves its cost when it's created and is charged only when the video is ready. If a generation fails, even because the first frame can't be downloaded, the full amount goes back to your balance.
Safe retries and spend limits
Send an Idempotency-Key and a resent request returns the task it already created instead of charging twice. Cap each key's hourly, daily or total spending in the console.
Try online, then integrate
The studio on this page runs the same Veo 3.1 model at the same prices, so what you test is what your users get. The docs also come as one llms.txt file for AI coding assistants, and the public status page shows each model's success rate.
Use cases
What You Can Build With the Veo 3.1 API
AI video generator apps
Turn prompts and photos into finished clips with sound in your own Veo 3.1 video generator, creative tool or content platform built on the Veo 3.1 API.
Ads and product videos
Animate a product photo into a launch clip or social ad with sound already in, then render the final cut in 4K once the idea works.
Storyboards and test shots
Try ideas at 720p with lite, the cheapest version, then render the shots you keep with standard or fast at 1080p or 4K.
Social media content
Create vertical 9:16 videos for TikTok, Reels and Shorts, or 16:9 clips for YouTube, with the sound already in, straight from your scheduling or creator tools.
Animated photos and artwork
Bring photos, illustrations and characters to life from a single first frame, or with lite move between a start and an end frame you choose.
Automated video pipelines
Connect the Veo 3.1 API to agents and content pipelines: create tasks in bulk, get the results by webhook and publish without manual steps.
FAQ
Veo 3.1 API FAQ
Can’t find what you need? Write to us.
01What is the Veo 3.1 API?
The Veo 3.1 API lets your app generate videos with sound using the Veo 3.1 model over HTTP. On NanoAPI you send POST /v1/tasks with model veo-3.1, a version (standard, fast or lite) and one of two modes (text_to_video or image_to_video), then get the finished video by webhook or by polling.
02How much does the Veo 3.1 API cost?
You pay per second of the video you ask for: duration × the price per second of the version and resolution. fast is cheaper than standard, and lite is the cheapest. Both modes cost the same, with or without sound. The live prices are in the table above, on the pricing page and in GET /v1/products, and the studio shows the exact cost before you generate. Failed runs are not charged.
03What's the difference between standard, fast and lite?
standard gives the best quality, fast costs less, and lite is the cheapest. standard and fast render at 720p, 1080p or 4K, always generate sound and expand your prompt into a detailed shot description. lite renders at 720p, follows your prompt as written, and is the only version that can add a last frame, use aspect_ratio auto to follow the first frame or turn the sound off.
04Can I try Veo 3.1 online before integrating?
Yes. Sign in and use the studio at the top of this page: it runs the same Veo 3.1 model at the same prices as the API and draws on the same balance, so you can check results and costs before writing code. Top-ups start at $10.
05How long can Veo 3.1 videos be, and which resolutions and aspect ratios are supported?
duration is 4, 6 or 8 seconds (8 when lite has a last frame). standard and fast render at 720p, 1080p or 4K, lite at 720p. aspect_ratio is 16:9 or 9:16; in image to video, match it to your first frame (16:9 for landscape, 9:16 for portrait), or let lite follow the first frame with auto. variant, mode, prompt, resolution, aspect_ratio and duration are required on every request.
06Does Veo 3.1 generate audio?
Yes. standard and fast always generate sound with the video and don't accept generate_audio. lite generates sound too unless you set generate_audio to false. The price is the same either way. The video with sound is at outputs[].url, and preview_url is a compressed copy without sound.
07How long does a Veo 3.1 video take to generate?
Most videos are ready in 1 to 2 minutes. In production, pass a webhook_url to be notified once when the task finishes instead of polling. Finished videos are kept for 15 days, so store the ones you need.
08What happens if a Veo 3.1 generation fails?
The amount reserved for the task goes back to your balance in full, and the task's error.type tells you why, for example a first frame that can't be downloaded. A request that breaks a version's rules, such as 1080p with lite or a last frame with standard, is rejected with a 400 error and no task is created, so nothing is reserved.
Start Creating With Veo 3.1
Try Veo 3.1 in the studio above, then bring the same model into your product with the Veo 3.1 API.