Video API

Text to Video API

AI video generation API for text-to-video and image-to-video.

Generate video from a prompt or an image on one REST endpoint. Plans from $21/mo. Eight self-hosted video models are unlimited on $149/mo.

Get API key See pricing

Self-hosted clips from $0.05
8 video models unlimited on $149/mo
Plans from $21/mo

Generate a video from a prompt with one request

Send a prompt and a model_id to POST /api/v7/video-fusion/text-to-video. The response has the output URL or a request id. Fetch the result with POST /api/v7/video-fusion/fetch/{id}, or pass a webhook URL and we post the result to you.

One subscription and one API key cover image, video, speech and LLM APIs. Creating an account is free. API calls need a plan, from $21 a month.

Trusted by

500M+

API Requests Processed

400K+

Registered Users

5K+

Discord Community Members

300+

Available AI APIs

500

GPUs in Our Own Datacenter

AI video generation API: one endpoint, many models

The model is a parameter. Set model_id to a self-hosted model such as wan2.2 or ltx-2.3, or to a partner model such as Kling, Veo or Seedance. The endpoint and the API key stay the same.

model_id: the video model to run.
prompt: the text that describes the clip.
duration: 4 to 30 seconds, where the model supports it.
aspect_ratio: for example 16:9 or 9:16.
webhook: a URL. We post the result to it when the clip is ready.

Self-hosted and partner video models

Eight video models run on our own GPUs. On Basic and Standard each clip is charged from the plan allowance. On the $149 Open Source Unlimited plan they have no per-clip charge. Partner models are priced per second.

Model	model_id	Basic ($21) and Standard ($47)	Open Source Unlimited ($149)
Self-hosted on our GPUs
Wan 2.2	wan2.2	$0.075 a clip	Unlimited on $149
LTX-2.3	ltx-2.3	$0.075 a clip	Unlimited on $149
SVD	svd	$0.05 a clip	Unlimited on $149
CogVideoX	cogvideox	$0.05 a clip	Unlimited on $149
Wan 2.1	wan2.1	$0.375 a 5-second clip	Unlimited on $149
MiniMax H3 text-to-video	h3-minimax-t2v	$0.05 per second	Unlimited on $149
MiniMax H3 reference-to-video	h3-minimax-r2v	$0.05 per second	Unlimited on $149
MiniMax H3 start-end-frame	h3-minimax-start-end-frame	$0.05 per second	Unlimited on $149
Partner models
Kling, Veo, Seedance, Sora, Hailuo, Wan 2.7	Set per model	Priced per second, from the plan allowance, then the wallet	Priced per second, billed from the wallet

Each plan is a dollar allowance, not a call count. Basic, Standard and Open Source Unlimited run 5, 10 and 15 generations in parallel. Video costs by plan are compared on the Cheapest AI video API page.

Start from an image instead

To animate a still image, send its URL in init_image (an array of image URLs) with a prompt to POST /api/v7/video-fusion/image-to-video. SVD and the MiniMax H3 reference-to-video and start-end-frame models run on our GPUs. Kling, Veo and Seedance work on the same endpoint.

Models, prices and a code sample are on the Image to Video API page.

Lip sync and video to video

The same API key covers two more video endpoints. Lip sync, at POST /api/v7/video-fusion/lip-sync, matches the mouth movement in a video to a new audio track. Video to video, at POST /api/v7/video-fusion/video-to-video, restyles a clip that you already have.

Parameters and samples are on the Lip Sync API page.

Text to video API quick start

Start a render, then get the result by webhook or with the fetch endpoint. Replace YOUR_MODELSLAB_API_KEY with the key from your dashboard.

Text to video with Python and a webhook (self-hosted Wan 2.2)

Python

1import requests
2
3response = requests.post(
4    "https://modelslab.com/api/v7/video-fusion/text-to-video",
5    headers={
6        "key": "YOUR_MODELSLAB_API_KEY",
7        "Content-Type": "application/json",
8    },
9    json={
10        "model_id": "wan2.2",
11        "prompt": "a cinematic drone shot of a city harbour at sunrise",
12        "aspect_ratio": "16:9",
13        # We post the finished clip to this URL.
14        "webhook": "https://example.com/modelslab-webhook",
15    },
16)
17
18print(response.json())

Text to video with JavaScript, then poll the fetch endpoint (partner model)

JavaScript

1const headers = {
2  'Content-Type': 'application/json',
3  key: 'YOUR_MODELSLAB_API_KEY',
4};
5
6const submit = await fetch('https://modelslab.com/api/v7/video-fusion/text-to-video', {
7  method: 'POST',
8  headers,
9  body: JSON.stringify({
10    model_id: 'kling-v3-t2v',
11    prompt: 'a product launch teaser with soft studio lighting and slow camera motion',
12    duration: 5,
13    aspect_ratio: '9:16',
14  }),
15});
16
17const { id, output } = await submit.json();
18
19// No output yet? Poll the fetch endpoint with the request id.
20let video = output?.[0];
21while (!video) {
22  await new Promise((resolve) => setTimeout(resolve, 5000));
23  const poll = await fetch(`https://modelslab.com/api/v7/video-fusion/fetch/${id}`, {
24    method: 'POST',
25    headers,
26  });
27  video = (await poll.json()).output?.[0];
28}
29
30console.log(video);

Text to video with cURL (partner model)

Bash

1curl https://modelslab.com/api/v7/video-fusion/text-to-video \
2  -H "key: YOUR_MODELSLAB_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model_id": "seedance-2-text-to-video",
6    "prompt": "an animated walkthrough of a modern mobile app dashboard",
7    "duration": 5,
8    "aspect_ratio": "16:9"
9  }'

Start Creating Amazing AI Videos in Minutes

Choose plan as per your needs, cancel anytime.

100% refund policy on monthly & yearly plans — cancel anytime

Contact Sales

Best Value

Open Source Unlimited

Mission-Critical

$149/month

🛡️ 100% refund policy · cancel anytime

Unlimited Open Source Models

100% refund policy

24x7 Support

15 parallel generations ⚡

Access to all APIs

Unlimited generations on all open-source models

For mission critical workloads

Add Team Members

Priority GPU Clusters

Standard

Production

$47/month

🛡️ 100% refund policy · cancel anytime

Moderate Traffic

100% refund policy

Priority Developer Support

10 concurrent API requests ⚡

For Production workloads

API access to all models

Prototype

Basic

Prototype

$21/month

🛡️ 100% refund policy · cancel anytime

Moderate Traffic

100% refund policy

Developer Support via Discord/Email

5 concurrent API requests ⚡

API access to all models

Shared GPU

Get your text to video API key

Plans start at $21 a month. The same key works for image, video, speech and LLM APIs.

Get API key

Image to Video API
Animate a still image into a short clip.
Cheapest AI video API
Per-clip prices for every video model.
Lip Sync API
Sync a face video to new speech.
Best AI video APIs in 2026
Video providers compared.
Cheapest AI API
Image, video and speech prices side by side.
Unlimited AI API
Every self-hosted open-source model for $149/mo.

Get Expert Support in Seconds

We're Here to Help.

Want to know more? You can email us anytime at support@modelslab.com

View Docs

Text-to-video, image-to-video, video-to-video, lip sync and motion control, each as its own endpoint under /api/v7/video-fusion/. One API key and one plan cover all of them.

Open-weight models ModelsLab self-hosts such as Wan and LTX, and third-party models including Kling, Veo, Seedance, Minimax, Runway and Vidu. You pick the model with `model_id`; the endpoint stays the same.

Plans start at $21/month (Basic) and $47/month (Standard). Self-hosted video models are paid from the usage included in your plan: SVD and CogVideoX cost $0.05 a clip, Wan 2.2 and LTX-2.3 $0.075. On the $149/month Open Source Unlimited plan the eight self-hosted video models have no per-clip charge. Partner models such as Kling, Veo and Seedance are priced per second. On Basic and Standard they use your plan's included usage first, then your wallet; on the $149 plan they bill from your wallet.

No. It is unlimited on the open-weight video models ModelsLab self-hosts. Partner models such as Kling, Veo and Seedance are priced per second: on Basic and Standard they use the plan's included usage first, then your wallet; on the $149 plan they bill from your wallet.

Short renders return an output URL in the response. Longer renders return an id; POST /api/v7/video-fusion/fetch/{id} until `output` is populated, or pass a `webhook` URL and ModelsLab posts the result to you.

ModelsLab is a paid service. Plans start at $21/month. Creating an account is free, but generating video requires an active plan.

Yes. One subscription and one API key cover image, video, speech and LLM generation. Self-hosted models are paid from the usage included in your plan. Partner models use that usage first on Basic and Standard, then your wallet; on the $149 plan they bill from your wallet.