GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →
Wan 2.5 Models

Wan 2.5 Models

Wan 2.5 enables synchronized audio-video generation in a single step, delivering richer detail, smoother motion, and more immersive storytelling.

Wan 2.5 enables synchronized audio-video generation in a single step, delivering richer detail, smoother motion, and more immersive storytelling.

All models

8 models
alibaba/wan-2.5/image-to-video
image-to-video$0.2500

alibaba/wan-2.5/image-to-video

WAN 2.5 converts text or images into videos (480p/720p/1080p) with synced audio, faster and more affordable than Google Veo3. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/image-to-video-fast
image-to-video$0.3400

alibaba/wan-2.5/image-to-video-fast

WAN 2.5 Fast converts text or images into synchronized-audio videos in 480p, 720p, or 1080p, offering faster, more affordable generation compared to Google Veo3. REST API, no coldstarts, affordable pricing.

alibaba/wan-2.5/text-to-video-fast
text-to-video$0.3400

alibaba/wan-2.5/text-to-video-fast

WAN 2.5 Fast creates synchronized-audio videos from text or images in 720p, faster and more affordable than Google Veo3. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/text-to-video
text-to-video$0.2500

alibaba/wan-2.5/text-to-video

WAN 2.5 makes 480p-1080p text/image-to-video with synced audio and is faster, more affordable than Google Veo3. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/video-extend
video-extend$0.2500

alibaba/wan-2.5/video-extend

WAN 2.5 Video-Extend turns short clips into longer videos with preserved or generated synchronized audio for continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/video-extend-fast
video-extend$0.3400

alibaba/wan-2.5/video-extend-fast

WAN 2.5 Fast is an AI-powered video extender that turns short clips into longer videos while preserving audio tracks for seamless extensions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/text-to-image
text-to-image$0.0300

alibaba/wan-2.5/text-to-image

WAN 2.5 Text-to-Image turns text prompts into AI-generated images with the WAN 2.5 model for on-demand image creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

alibaba/wan-2.5/image-edit
image-to-image$0.0350

alibaba/wan-2.5/image-edit

Refine existing visuals with WAN 2.5 image-edit using prompt-driven adjustments and stylistic upgrades for photos and graphics. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Wan 2.5 Models

Alibaba Wan 2.5 is a production-ready AI image and video generation model suite for text-to-video, image-to-video, text-to-image, image editing, and video extension workflows. Designed for fast iteration and sound-on content creation, Wan 2.5 supports HD video generation, audio-visual synchronization, multilingual prompt workflows, and flexible 3–10 second video outputs.

Built for creators, developers, marketers, and AI video applications, Wan 2.5 helps generate videos from prompts or images, create visual assets, edit existing images, and extend video clips into longer scenes. It is suitable for social media shorts, product ads, e-commerce videos, explainers, tutorials, storytelling, and scalable creative production pipelines.

Core Model Capabilities

Text-to-Video Generation:

Create HD videos directly from natural-language prompts with coherent motion, cinematic framing, synchronized audio, and strong scene understanding.

Image-to-Video Generation:

Animate still images into dynamic video clips while preserving subject identity, composition, visual style, and scene continuity.

Text-to-Image Generation:

Generate high-quality images from text prompts for product visuals, key frames, concept art, social media assets, and creative exploration.

AI Image Editing:

Edit and refine existing images with controlled changes while preserving subject structure, visual consistency, and important image details.

Video Extension:

Extend short video clips into longer continuous videos while maintaining motion flow, visual style, and scene coherence.

Audio-Visual Synchronization:

Generate videos with aligned voice, sound effects, music, and visual timing, making Wan 2.5 useful for sound-on ads, explainers, tutorials, and social media clips.

Audio-Driven Creative Control:

Use voice, sound effects, or background music as references to guide pacing, mood, motion, and scene rhythm.

Flexible HD Video Output:

Support 480p, 720p, and 1080p video generation with 3–10 second duration options for different quality, cost, and platform requirements.

Production-Ready API:

Access Wan 2.5 models through scalable APIs for automated content generation, fast creative testing, and commercial image and video workflows.

Wan 2.5 Models on WaveSpeedAI give creators and developers fast access to Alibaba’s audio-aware image and video generation tools with flexible pricing, scalable API access, and production-ready creative quality.

Wan 2.5 Models API — pricing & performance

Run any model in the Wan 2.5 Models collection through a single REST API. Pay per generation — no subscriptions, no minimums — with industry-leading latency on a 99.9% uptime infrastructure.

Why run Wan 2.5 Models on WaveSpeedAI

Transparent pricing

Per-call pricing for every Wan 2.5 Models model. The price is listed on each model page — no platform fees on top.

Optimized for low latency

Most Wan 2.5 Models image models complete in under 2 seconds. Video and 3D models run several times faster than self-hosted alternatives.

99.9% uptime

Multi-region failover and automatic retries keep your production traffic online — even during provider outages.

Frequently asked questions

How much does the Wan 2.5 Models API cost?+

Each model has its own per-call price listed on the model page. We bill per successful generation, with no subscription fees or minimums.

How fast are Wan 2.5 Models models on WaveSpeedAI?+

Image models in this collection typically complete in under 2 seconds. Video and 3D models depend on duration and resolution but are usually several times faster than self-hosted runs.

Can I try the API without a credit card?+

Eligible new accounts may receive $1 in promotional credits to try Wan 2.5 Models models without a credit card. Trial credits are not guaranteed for every signup; check your account balance before generating.

Are there rate limits?+

Standard accounts have generous concurrent-job limits. Enterprise plans offer custom RPM, higher concurrency, and dedicated capacity — contact sales for details.