Google DeepMind (Gemini) / veo-3.1-fast

Veo 3.1 Fast

Veo 3.1 Fast is Google's Veo video model for high-quality motion, realistic scenes, and cinematic clips.

Video generation

Context

tokens

Input

$0.109

/ second

Output

$0.109

/ second

Quality

#99

Elo 1110

Overview

What this model is good for

Veo 3.1 Fast is Google's Veo video model for high-quality motion, realistic scenes, and cinematic clips.

Model capabilities

Video output

Can produce video output for generation or editing workflows.

Model maker

Model maker and access

This section shows the model maker, SeaLink model ID, protocol, and pricing information.

Google DeepMind (Gemini)

Called through SeaLink's unified account, balance, and OpenAI-compatible API.

Protocol

Video generation API

Base URL: https://test.sealink.io/v1

Pricing

Pricing and cost sense

Prices come from the current model catalog. Simple estimates help users judge whether the model fits production volume.

Input$0.109/ second

Output$0.109/ second

Actual billing follows usage logs and billing records; caching and media pricing depend on the endpoint.

API

Copy into your code

The model page should make it clear which model to copy, which base URL to use, and where to get an API Key.

model

veo-3.1-fast

base_url

https://test.sealink.io/v1

Auth

Bearer $SEALINK_API_KEY

cURL

# Step 1: Submit video generation
curl https://test.sealink.io/v1/video/generations \
  -H "Authorization: Bearer $SEALINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1-fast",
    "prompt": "A cat walking along a beach at sunset",
    "size": "1280x720",
    "seconds": "5"
  }'

# Step 2: Poll for result (use task id from submit response)
curl https://test.sealink.io/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $SEALINK_API_KEY"

Python (OpenAI SDK)

import requests, time

api_key = "<your-sealink-key>"
base = "https://test.sealink.io"

# Submit
resp = requests.post(f"{base}/v1/video/generations", json={
    "model": "veo-3.1-fast",
    "prompt": "A cat walking along a beach at sunset",
    "size": "1280x720",
    "seconds": "5",
}, headers={"Authorization": f"Bearer {api_key}"})
task = resp.json()
task_id = task["id"]

# Poll until complete
while True:
    time.sleep(5)
    r = requests.get(f"{base}/v1/tasks/{task_id}",
        headers={"Authorization": f"Bearer {api_key}"})
    v = r.json()
    if v["status"] == "completed":
        print(v.get("data") or v.get("upstream_response") or v)
        break

Node.js (OpenAI SDK)

const base = "https://test.sealink.io";
const headers = { Authorization: `Bearer ${process.env.SEALINK_API_KEY}` };

// Submit
const resp = await fetch(`${base}/v1/video/generations`, {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify({
    model: "veo-3.1-fast",
    prompt: "A cat walking along a beach at sunset",
    size: "1280x720",
    seconds: "5",
  }),
});
const task = await resp.json();
const taskId = task.id;

// Poll until complete
let video;
do {
  await new Promise(r => setTimeout(r, 5000));
  const r = await fetch(`${base}/v1/tasks/${taskId}`, { headers });
  video = await r.json();
} while (video.status !== "completed");
console.log(video.data || video.upstream_response || video);