dreamtoai

Google/veo-3.1

Veo 3.1 是一种用于生成 8 秒视频（720p、1080p 或 4k）的模型，可原生生成音频。

OperationalText to VideoImage to Video-20%vs officialPriced by requestCommercial useData privacy

Inputlive schema

No test requests yet. Send your first request.

Output

Run the form on the left. Results, polling status and cURL appear under the form.

Pricing

This model is priced by the usage dimensions listed here. Compare all pricing.

List prices in USD. Your effective price also depends on the billing group attached to your API key.

Criteria4 - 720pveo-3.1
$1.28per request1.6/次
Criteria6 - 720pveo-3.1
$1.92per request2.4/次
Criteria8 - 720pveo-3.1
$2.56per request3.2/次
Criteria8 - 1080pveo-3.1
$2.56per request3.2/次

API

POST/v1/jobs
const BASE_URL = "https://api.dreamtoai.com";
const API_KEY = process.env.MIX_API_KEY;

const headers = {
  "Authorization": `Bearer ${API_KEY}`,
  "Content-Type": "application/json",
};

const payload = {
  "model": "veo-3.1",
  "input": {
    "prompt": "一段自然纪录片风格的雪山航拍镜头",
    "image": "https://example.com/image.png",
    "lastframe": [
      "https://example.com/ref.png"
    ],
    "referenceImages": [
      "https://example.com/ref.png"
    ],
    "video": [
      "https://example.com/ref.mp4"
    ],
    "aspectratio": "16:9,9:16",
    "resolution": "720p,1080p,4k",
    "generate_audio": false,
    "negative_prompt": "低清晰度、闪烁、变形",
    "durationseconds": "4,6,8"
  }
};

const submit = await fetch(`${BASE_URL}/v1/jobs`, {
  method: "POST",
  headers,
  body: JSON.stringify(payload),
}).then((r) => r.json());

const status = await fetch(`${BASE_URL}/v1/jobs/${submit.id}`, { headers })
  .then((r) => r.json());
console.log(status);

Create a key in Console → API Keys and replace the placeholder in the sample.

README

veo-3.1

Veo 3.1 是一种用于生成 8 秒视频（720p、1080p 或 4k）的模型，可原生生成音频。

Why Choose This?

Text-to-video generation
Turns natural-language prompts into video clips.
Predictable pricing
From $1.28 per request, billed only for what you run.
Several output options
Choose between 4 - 720p, 6 - 720p, 8 - 720p, 8 - 1080p.
Async job API
Submit a job and poll for the result, so long renders never hold a connection open.
One key for every model
The same API key works for every model on dreamtoai.

Parameters

ParameterRequiredDescription
promptstringRequiredText description of what to generate.
imageimageOptionalReference image to guide the result.
lastframestringOptional参考图 URL
referenceImagesstringOptional参考图 URL
videovideoOptional参考视频 URL
aspectratiostringOptional画幅比例 Default: 16:9.
resolutionstringOptionalOutput resolution. Default: 720p.
generate_audiobooleanOptionalGenerate synchronized audio with the video. Default: false.
negative_promptstringOptionalWhat to keep out of the result.
durationsecondsstringOptional时长 Default: 4.

How to Use

  1. Try it here first — Sign in and run the model in the playground above to check the output before you write code.
  2. Create an API key — Open Console → API Keys and create a key. The same key works for every model.
  3. Write your prompt — Describe the scene, action, camera movement, lighting and mood.
  4. Set optional parameters — Adjust the optional parameters listed above to control the output.
  5. Submit the job — Send POST /v1/jobs with the model ID veo-3.1. The response returns a job ID.
  6. Poll for the result — Call GET /v1/jobs/{job_id} every few seconds until the job finishes, then read the output URLs.

Writing Effective Prompts

Write the prompt like a shot list: the more you direct, the more the model delivers.

1. One-line summary

Open with subject, setting, action, style and camera in one sentence.

A cyclist rides along a foggy forest road at dawn, cinematic, slow side tracking shot.

2. Timeline for longer clips

Split the clip into timed beats, such as 0–3s and 3–6s, and give each beat one clear action.

3. Camera language

Use shot sizes (wide, medium, close-up) and moves (push in, pan, orbit, handheld) directly.

4. Consistency notes

End with what holds for the whole clip: lighting, color palette, mood and sound.

Prompt
Weaka dog running
StrongA golden retriever sprints across a wet beach at sunset, chasing a red ball. 0–2s: low tracking shot beside the dog, sand spraying. 2–5s: it catches the ball and turns to the camera, slow push in. Warm backlight, light sea spray, shallow depth of field, only the sound of waves.

Pricing

Billing itemPriceOfficial price
4 - 720p$1.28 per request$1.60/次
6 - 720p$1.92 per request$2.40/次
8 - 720p$2.56 per request$3.20/次
8 - 1080p$2.56 per request$3.20/次

That is 20% below the official list price.

Example: 10 runs at 4 - 720p cost $12.80.

List prices in USD. Your effective price also depends on the billing group attached to your API key. Compare all pricing

Best Use Cases

  • Short-form social video — Create vertical and square clips for social feeds.
  • Ads and product promos — Generate promotional clips and product scenes.
  • Storyboards and previs — Turn scripts into motion previews for pitching and planning.
  • Explainers and education — Visualize ideas, processes and stories.
  • Music and mood clips — Produce atmospheric loops and visuals for music.
  • Game and film concepts — Test scenes, camera moves and styles before production.

Pro Tips

  • Test prompts at the shortest duration and lowest resolution, then scale up.
  • Give each timed beat one clear action to avoid jump cuts.
  • Use 16:9 for widescreen and 9:16 for vertical social video.
  • Describe the camera movement explicitly; otherwise the model picks one for you.
  • Poll the job status with a growing interval instead of hammering the endpoint.

Browse all video modelsBrowse API Market

FAQ

What is veo-3.1?

Veo 3.1 是一种用于生成 8 秒视频（720p、1080p 或 4k）的模型，可原生生成音频。

How do I call the veo-3.1 API?

Send POST /v1/jobs with the model ID veo-3.1 and your API key. Ready-to-run samples are in the API section above.

How is billing calculated?

Requests are billed at the prices listed above and charged to your wallet. Final cost depends on usage and the billing group attached to your API key.

Where do I get an API key?

Create one in Console → API Keys. The same key works for every model on the gateway.

Can I use the output commercially?

Yes. You can use what you generate in commercial projects, subject to the model provider’s terms.

About veo-3.1 on dreamtoai

Veo 3.1 是一种用于生成 8 秒视频（720p、1080p 或 4k）的模型，可原生生成音频。

Related models

Next steps

Compare pricingBrowse API MarketCreate an account