Wan 3.0 and Seedance 2.5 Turbo
Low-cost drafts: iterate on prompts, A/B variants and volume before a final render.
Text-to-video · Image-to-video · REST API
AI Video Generation API
Generate text-to-video and image-to-video clips with ByteDance Seedance 2.5, Kuaishou Kling 3.0, Google Veo 3.1 Fast, Alibaba Wan 3.0 and Google Gemini Omni through one API key and one request shape. Preview the exact cost of any clip, then poll for the MP4.
cURL · Wan 3.0
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/wan30/generations \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Idempotency-Key: wan30-001" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Handheld shot of a creator unboxing sneakers on a sunny balcony, natural light, street ambience",
"aspectRatio": "9:16",
"duration": 5,
"resolution": "720p",
"generateAudio": true
}
}'How It Works
Get Started
Create an API key
In Dashboard → Developer API → Keys, create a revocable mi_ key and send it as a Bearer token.
Preview the cost
POST the same input to preview-credits and get the exact credit quote back. Previews never charge.
Generate and poll
POST to /models/{modelId}/generations, receive HTTP 202 with a generation ID, then poll the video status endpoint until terminal is true.
Video API pricing
Every video model on one endpoint, quoted per clip
Each row is a real clip request with native audio, quoted with the live model pricing when this page was built: 5-second image-to-video clips on Wan, Seedance and Kling, and 8-second text-to-video clips on Veo 3.1 Fast and Gemini Omni. Drop startFrameUrl and the same body becomes text-to-video.
| Model ID | Model creator | Quoted request | Typical time | Credits |
|---|---|---|---|---|
| wan30 | Alibaba Wan 3.0 | 5 s, 720p, audio | ~60s | 25,063 |
| wan30prime | Alibaba Wan 3.0 Prime | 5 s, 720p, audio | ~30s | 37,594 |
| seedance25turbo | ByteDance Seedance 2.5 Turbo | 5 s, 720p, audio | ~45s | 50,126 |
| seedance25 | ByteDance Seedance 2.5 | 5 s, 720p, audio | ~90s | 90,226 |
| kling_v30_std | Kuaishou Kling v3.0 Standard | 5 s, audio | ~90s | 31,579 |
| kling_v30_pro | Kuaishou Kling v3.0 Pro | 5 s, audio | ~90s | 42,106 |
| veo31 | Google Veo 3.1 Fast | 8 s, 1080p, audio | ~90s | 60,151 |
| gemini-omni-11-flash | Google Gemini Omni 1.1 Flash | 8 s, 720p, audio | ~40s | 40,101 |
Quotes are calculated from the live model pricing when this page is built. POST /models/{modelId}/preview-credits returns the exact cost of your own payload without charging.
Quickstart
Text-to-video with Wan 3.0 in one request
One POST creates the job and returns HTTP 202 with a generation ID. Add startFrameUrl for image-to-video, change the model ID to switch models, then poll the video status endpoint until terminal is true.
POST
https://www.makeinfluencer.ai/api/v1/models/wan30/generationscURL
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/wan30/generations \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Idempotency-Key: wan30-001" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Handheld shot of a creator unboxing sneakers on a sunny balcony, natural light, street ambience",
"aspectRatio": "9:16",
"duration": 5,
"resolution": "720p",
"generateAudio": true
}
}'POST · preview-credits · no charge
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/wan30/preview-credits \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Handheld shot of a creator unboxing sneakers on a sunny balcony, natural light, street ambience",
"aspectRatio": "9:16",
"duration": 5,
"resolution": "720p",
"generateAudio": true
}
}'GET · poll until terminal
curl \
https://www.makeinfluencer.ai/api/v1/generations/video/GENERATION_ID \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY"Features
What you get with the video generation API
01
Every major video model, one contract
prompt, startFrameUrl, endFrameUrl, duration, aspectRatio, resolution and generateAudio mean the same thing on every video model ID.
02
Text-to-video and image-to-video in one call
Send a prompt for text-to-video, or add startFrameUrl and the same endpoint animates your image. No separate route to pick.
03
Native audio
Seedance 2.5, Kling 3.0, Veo 3.1 Fast, Wan 3.0 and Gemini Omni can render synchronized sound, dialogue and ambience with the video.
04
No separate API plan
REST, MCP and the dashboard draw from the same credit balance at the same model prices, with no monthly API fee.
05
Safe retries
Send an Idempotency-Key header and a retried request with the same body replays the original response instead of starting a second job.
06
Also in Claude and Cursor
The same models are available through the MCP connector, so an agent can generate videos on your account.
Price check
What the same clips list for on fal.ai
Public list prices for comparable requests elsewhere, verified 29 September 2026, next to our credit quote for the same request. Our credits come from the balance you already use in the app, and preview-credits returns the exact figure before you spend anything.
| Model | Provider | Their list price | Their example | Our model ID | Our credits, same request |
|---|---|---|---|---|---|
| Seedance 2.5 image-to-video | fal.ai | ~$0.473/s at 720p, ~$0.2205/s at 480p | ~$2.37 for 5 s at 720p | seedance25 | 90,226 (5 s, 720p, audio) |
| Kling 3.0 Pro image-to-video | fal.ai | $0.112/s audio off, $0.168/s audio on | $0.56 silent or $0.84 with audio for 5 s | kling_v30_pro | 42,106 (5 s, audio) |
| Veo 3.1 Fast | fal.ai | $0.10/s silent, $0.15/s with audio (720p/1080p) | $1.20 for 8 s at 1080p with audio | veo31 | 60,151 (8 s, 1080p, audio) |
Third-party prices are copied from each provider's public model page on 29 September 2026 and can change at any time. Sources: https://fal.ai/models/bytedance/seedance-2.5/image-to-video, https://fal.ai/models/fal-ai/kling-video/v3/pro/image-to-video, https://fal.ai/models/fal-ai/veo3.1/fast.
Choosing a video model
Which video generation API should you call?
Draft on Wan 3.0 or Seedance 2.5 Turbo, render finals on Seedance 2.5, Kling 3.0 Pro or Veo 3.1 Fast, and switch by changing one model ID. Inputs are normalised, so prompt, startFrameUrl, duration, resolution and generateAudio mean the same thing on every video model.
Seedance 2.5 and Kling 3.0 Pro
Cinematic motion, native audio and end-frame control for final renders.
Veo 3.1 Fast and Gemini Omni
Google's video models with synchronized audio, up to 4K on Gemini Omni.
Practical workflow
- 1
Create a key
Dashboard → Developer API → Keys. Keys start with mi_.
- 2
Upload a start frame
POST /assets/presign, upload, then pass the URL in startFrameUrl.
- 3
Preview and generate
Quote the body with preview-credits, then POST it to generations.
- 4
Poll and store
Poll GET /generations/video/{id} and save the url when ready is true.
Model names belong to their creators: Seedance (ByteDance), Wan (Alibaba), Kling (Kuaishou), Veo and Gemini (Google). MakeInfluencer.ai is an independent API provider and is not affiliated with or endorsed by them.
Trusted by over 300,000+ creators
FAQ
Frequently Asked Questions
Add video generation to your product today
Create an API key, preview a request and render your first clip in a few minutes, with the same credits you use in the app.
Start creating in minutes · Pay as you go