Veo 3.1 Lite API

Google's lightweight video model for text and first-frame generation, with landscape or portrait output and optional native audio.

720p · no audio
Google $0.03 / second
1080p · no audio
Google $0.05 / second
1080p · audio
Google $0.08 / second
4s · 720p · audio
KIE $0.0188 / second
Official$0.0563% less

Compare prices

Compare public channel prices for the same output specification

Compare other models
Output specificationProvidersPublished provider priceTypical timeTry it
720p · no audio
GoogleOfficial
$0.0300 / second
Try it
NanoAPI
$0.0585 / second95% more
Try it
1080p · no audio
GoogleOfficial
$0.05 / second
Try it
1080p · audio
GoogleOfficial
$0.08 / second
Try it
4s · 720p · audio
GoogleOfficial
$0.0500 / second
Try it
NanoAPI
$0.0585 / second17% more
Try it
KIE
$0.0188 / second63% less
Typical time 1 min
1 minTry it
6s · 720p · audio
GoogleOfficial
$0.0500 / second
Try it
NanoAPI
$0.0585 / second17% more
Try it
KIE
$0.0125 / second75% less
Typical time 1 min
1 minTry it
8s · 720p · audio
GoogleOfficial
$0.0500 / second
Try it
NanoAPI
$0.0585 / second17% more
Try it
KIE
$0.0094 / second81% less
Typical time 1 min
1 minTry it

Automatic routing and failover

Call Veo 3.1 Lite with one model ID and Yir picks the channel for each job from Google, NanoAPI, and KIE: it goes to the eligible channel with the lowest estimated price and is billed at that channel's public price, with no markup. If an attempt is confirmed failed, Yir retries on another channel within your max_cost. No routing parameters needed in your request. Routing and fallback docs

Pricing notes

Billed by the channel that actually runs the job. Failover may switch channels, which can change cost and time.

Use the API

Hand the code to a coding agent, generate right in the chat with MCP or the Skill, or integrate yourself with the SDK or the OpenAI-compatible API.

Let a coding agent integrate it

Copy the integration prompt, or open it directly in Codex or Claude. The agent reads this page and the model contract, then writes submit, wait and result handling into your project.

Add the Yir MCP server

Connect it to ChatGPT, Claude or Cursor, then mention @Yir and ask for Veo 3.1 Lite by name. It quotes first and only generates after you confirm.

https://gateway.yir.ai/mcp
Setup steps for each client

One command for Claude Code

Create an API key in the console, set it as YIR_API_KEY, then run:

claude mcp add --transport http yir https://gateway.yir.ai/mcp --header "Authorization: Bearer $YIR_API_KEY"

Install the Yir Skill

Set YIR_API_KEY where your agent runs, add the Skill to Claude Code, Codex or another coding agent, then say “use Veo 3.1 Lite on Yir to make…”.

npx skills add yir-ai/skills
About the Yir Skill

Install the official SDK with your package manager, or copy the code snippet below to get started

$pnpm add @yir-ai/sdk
import { createNodeYirClient } from "@yir-ai/sdk/server";
 
// Reads YIR_API_KEY from the environment by default: process.env.YIR_API_KEY
const client = createNodeYirClient();
 
// 1. Submit a video generation job
const job = await client.submitVideo({
model: "google/veo-3.1-lite-generate-001",
input: {
type: "text",
prompt: "A sea turtle swims slowly over a coral reef. The camera tracks smoothly from the side as sunlight filters through clear water, casting moving patterns across its shell",
},
parameters: {
duration: 8,
resolution: "720p",
aspect_ratio: "16:9",
generate_audio: true,
n: 1,
},
});
 
// 2. Wait for the job to finish and deliver its result
const result = await client.waitForJob(job.id);
console.log("Delivered files:", result.result);
if (result.result && "files" in result.result) {
for (const file of result.result.files) {
console.log("->", file.url);
}
}

Projects already on the OpenAI protocol, or gateways such as new-api, only need a new Base URL and key. OpenAI compatibility guide

OpenAI SDK base_url
https://gateway.yir.ai/openai/v1
new-api channel Base URL
https://gateway.yir.ai/openai
Key
Yir API key
Model ID
google/veo-3.1-lite-generate-001
curl https://gateway.yir.ai/openai/v1/videos \
  -H "Authorization: Bearer $YIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/veo-3.1-lite-generate-001",
    "prompt": "A sea turtle swims slowly over a coral reef. The camera tracks smoothly from the side as sunlight filters through clear water, casting moving patterns across its shell",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "seconds": "8"
  }'

Parameter overview

Common parameters; limits depend on the current model and selected channel

API docs
Resolution
resolution
  • 720p
  • 1080p

Output resolution tier. Higher resolutions offer sharper pixel fidelity and scale pricing accordingly

Aspect ratio
aspect_ratio
  • 16:9
  • 9:16

Geometric aspect ratio. Choose according to target medium (portrait, banner, or square)

Input mode
input_mode
  • Text input
  • Image input

Reference limits and formats depend on the model and selected channel

Duration
duration
  • 4 seconds
  • 6 seconds
  • 8 seconds

Video output duration tier, billed per second or stepped tier

Audio
generate_audio
  • Optional

Optional synchronized native audio generation track

References
references
  • first_frame ≤ 1

Reference limits across input modes depend on the selected channel. Counts in the price table are examples, not input limits or free allowances.

Frequently asked questions

Start building with Veo 3.1 Lite

Compare the same spec across providers and call multiple providers from one wallet.