Home
/
Models
/
Wan 3.0 Video

Wan 3.0 Video API

Wan 3.0 Video is Alibaba Cloud's all-in-one reference-based video generation model, supporting text-to-video, image-to-video, and reference-based generation up to 30 seconds long.
Output
$0.065–$0.26 / sec (by resolution)
Released
Aug 6, 2026
Try now
View Docs

How to use Wan 3.0 Video API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/wan3.0-video.

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Wan 3.0 Video API Pricing

TypePrice
Input
Output
$0.065–$0.26 / sec (by resolution) tokens

480p $0.065/sec, 720p $0.13/sec, 1080p $0.26/sec.

Wan 3.0 Video vs other models

ModelInputOutputContextBest for
Wan 3.0 Video
This page
$0.065–$0.26 / sec (by resolution)
All-in-one video generation
Veo 3.1
$0.26 / sec (variable)
Video generation
Sora 2
$0.13 / sec (variable)
Video generation
Gemini Omni
$11.7 / 1M
Video generation
Seedance 2.0
$0.3944 / per second
Cinematic video + native audio

Related chat models

Kling 3.0 Standard Image to Video
Kling AI
Input
Output
$0.1092 / sec (variable)
View model →
Veo 3.1 Image-to-Video
Google
Input
Output
$0.21 / sec (variable)
View model →
Sora 2 Image-to-Video
OpenAI
Input
Output
$0.13 / sec (variable)
View model →
Kling 2.5 Turbo Pro Text to Video
Kling AI
Input
Output
$0.091 / sec (variable)
View model →

Related blog posts

Best AI Models for Agentic Workflows and Tool Use in 2026

Agentic workflows are AI systems that plan, act, and use tools autonomously. Pick the wrong model, and automations fail while compute is wasted.

Read article →

Best LLMs for Long-Context & Multimodal Tasks in 2026

The unified AI API that puts every frontier model one call away. This guide cuts through the noise so you pick the right model for the job, not the most hyped one.

Read article →

Start building with Wan 3.0 Video

Get API Key
1000+ models, one API.