Wan 2.6 API
Alibaba WAN 2.6 — text-to-video and image-to-video with synced audio at 720p/1080p, plus reference-to-video, video-extend, image-edit, and text-to-image in the same family. Flash and Spicy tiers for speed and scalable content generation.
Text-to-video and image-to-video at 720p/1080p with synced audio. Image-to-video Flash for speed-optimized generation; Spicy for unlimited scalable content. Reference-to-video preserves identity from character, prop, or scene references. Video-extend supports preserved or generated synchronized audio.
About the Wan 2.6 API
What Wan 2.6 does, how it fits in the Alibaba model lineup, and why teams reach for it.
Wan 2.6 is a video generation model from Alibaba, available through the WaveSpeedAI REST API. Alibaba WAN 2.6 — text-to-video and image-to-video with synced audio at 720p/1080p, plus reference-to-video, video-extend, image-edit, and text-to-image in the same family. Flash and Spicy tiers for speed and scalable content generation.
Text-to-video and image-to-video at 720p/1080p with synced audio. Image-to-video Flash for speed-optimized generation; Spicy for unlimited scalable content. Reference-to-video preserves identity from character, prop, or scene references. Video-extend supports preserved or generated synchronized audio.
The Wan 2.6 family on WaveSpeedAI ships 10 REST endpoints covering Text-To-Image, Image-To-Video, Video-Extend, Image-To-Image, Text-To-Video workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Wan 2.6 through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Wan 2.6 API endpoints
10 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.
Text To Image
WAN 2.6 Text-to-Image generates high-quality images from natural-language prompts with strong prompt adherence and clean composition. It supports multiple aspect ratios and size control, seed-based reproducibility, and flexible styles (photorealistic to illustrative) for ads, product shots, and social visuals. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.
Image To Video Pro
WAN 2.6 Image-to-Video Pro converts images into premium-quality videos with superior motion dynamics, enhanced visual fidelity, and professional cinematic output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Video Extend
WAN 2.6 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.
Reference To Video
WAN 2.6 Reference-to-Video turns character, prop, or scene references—single or multi-view—into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Image Edit
WAN 2.6 Image-Edit turns prompts into precise photo edits—adjusting color and lighting, restyling aesthetics, replacing backgrounds, removing objects, and refining details while preserving subject identity. Built for stable, repeatable image-to-image pipelines. Ready-to-use REST API, best performance, no cold starts, affordable pricing.
Text To Video
WAN 2.6 Text-to-Video turns plain prompts into coherent, cinematic clips with crisp detail, stable motion, and strong instruction-following—great for ads, explainers, and social posts. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Image To Video Flash
WAN 2.6 Flash converts images into videos (720p/1080p) with optional audio, optimized for speed and cost. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Reference To Video Flash
WAN 2.6 Reference-to-Video Flash turns character, prop, or scene references from images or videos into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Flash version with faster generation speed. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Image To Video Spicy
WAN 2.6 Spicy converts images into unlimited high-quality videos with smooth animations optimized for scalable content generation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Image To Video
WAN 2.6 converts text or images into videos (720p/1080p) with synced audio, faster and more affordable than Google Veo3. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
See Wan 2.6 in action
Real outputs generated by the Wan 2.6 API. Hover any video to preview, click to open the full-size viewer.
How to use the Wan 2.6 API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/text-to-video. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from"queued" or"processing" to"completed".
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Wan 2.6 variant you called.
What you can build with Wan 2.6
Common workflows developers and creators use the Wan 2.6 API for.
Text-to-video with synced audio
alibaba/wan-2.6/text-to-video turns plain prompts into coherent cinematic clips with crisp detail, stable motion, and synced audio — catalog framing: great for ads, explainers, and social posts.
Image-to-video at 720p/1080p
alibaba/wan-2.6/image-to-video converts images into videos at 720p/1080p with synced audio — faster and more affordable than Google Veo3 per the catalog positioning.
Reference-to-video for identity
alibaba/wan-2.6/reference-to-video turns character, prop, or scene references (single or multi-view) into new video shots with preserved identity, style, and layout plus smooth coherent motion.
Video-extend with audio continuity
alibaba/wan-2.6/video-extend turns short clips into longer videos with preserved or generated synchronized audio for continuity — useful for building extended sequences from shorter source clips.
Image-edit in the same family
alibaba/wan-2.6/image-edit performs precise photo edits — adjusting color and lighting, restyling aesthetics, replacing backgrounds, removing objects — while preserving subject identity.
Flash and Spicy tiers
image-to-video-flash optimizes for speed and cost; image-to-video-spicy generates unlimited high-quality videos optimized for scalable content generation — pick Flash for iteration, Spicy for high-volume i2v pipelines.
Tips for prompting Wan 2.6
Practical advice for getting better outputs from Wan 2.6 — drawn from the patterns that work across video models in production pipelines.
Synced audio — describe sound in the prompt
Wan 2.6 ships synced audio on text-to-video and image-to-video. Describe ambient sound, dialogue mood, or music genre alongside the visual prompt.
Flash tier for iteration, Standard for delivery
image-to-video-flash optimizes for speed and cost; standard image-to-video and text-to-video for delivery-grade output with synced audio.
Reference-to-video for identity
Use reference-to-video when character, prop, or scene identity must carry from reference images to the generated clip — single or multi-view refs supported.
Video-extend with audio continuity
video-extend preserves or generates synchronized audio across the extension — useful when building longer clips from short source material.
Cross-modal: image-edit + video in one family
Generate stills with text-to-image, refine with image-edit, then animate with image-to-video — all under alibaba/wan-2.6/* without switching model families.
Spicy for high-volume i2v
image-to-video-spicy is positioned for unlimited scalable content generation — pick for throughput-friendly stylized i2v pipelines.
Wan 2.6 API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| alibaba/wan-2.6/text-to-image | text-to-image | $0.030 |
| alibaba/wan-2.6/image-to-video-pro | image-to-video | $0.60 |
| alibaba/wan-2.6/video-extend | video-extend | $0.25 |
| alibaba/wan-2.6/reference-to-video | image-to-video | $0.50 |
| alibaba/wan-2.6/image-edit | image-to-image | $0.035 |
| alibaba/wan-2.6/text-to-video | text-to-video | $0.50 |
| alibaba/wan-2.6/image-to-video-flash | image-to-video | $0.13 |
| alibaba/wan-2.6/reference-to-video-flash | image-to-video | $0.13 |
| alibaba/wan-2.6/image-to-video-spicy | image-to-video | $0.50 |
| alibaba/wan-2.6/image-to-video | image-to-video | $0.50 |
Call the Wan 2.6 API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("alibaba/wan-2.6/text-to-video", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"alibaba/wan-2.6/text-to-video",
{}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.6 vs alternatives
When to pick Wan 2.6 over similar models on WaveSpeedAI.
Wan 2.6 vs Wan 2.7
Wan 2.7 is the newer architecture with image-edit-pro, text-to-image-pro with thinking mode, and first/last frame control on image-to-video. Wan 2.6 is positioned as faster and more affordable with synced audio and the Flash/Spicy tier story.
Wan 2.6 vs Wan 2.2
Wan 2.2 (WaveSpeedAI variants) ships specialized endpoints — Animate (120s), Speech-to-Video (10-min), Fun-Control (Apache 2.0), LoRA trainers. Wan 2.6 is the official Alibaba family with synced audio and cross-modal image-edit/text-to-image in one namespace.
Wan 2.6 vs Seedance 2.0
Seedance 2.0 ships native audio across every variant and the Turbo tier. Wan 2.6 adds reference-to-video, video-extend, image-edit, and text-to-image in the same family — broader cross-modal toolkit at a different price point.
Wan 2.6 API — Frequently asked questions
Pricing, license, integration — common questions about running Wan 2.6 on WaveSpeedAI.
What is the Wan 2.6 API?
Wan 2.6 is a Alibaba video generation model exposed as a REST API on WaveSpeedAI. Alibaba WAN 2.6 — text-to-video and image-to-video with synced audio at 720p/1080p, plus reference-to-video, video-extend, image-edit, and text-to-image in the same family. Flash and Spicy tiers for speed and scalable content generation. You can call it programmatically or try it from the playground linked above.
How do I call the Wan 2.6 API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/text-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to "completed", then read the output URL from data.outputs[0]. Full Python / Node.js / cURL examples are above.
How much does the Wan 2.6 API cost?
Wan 2.6 starts at $0.030 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Wan 2.6 variants are available?
WaveSpeedAI hosts 10 Wan 2.6 endpoints: alibaba/wan-2.6/text-to-image, alibaba/wan-2.6/image-to-video-pro, alibaba/wan-2.6/video-extend, alibaba/wan-2.6/reference-to-video, alibaba/wan-2.6/image-edit, alibaba/wan-2.6/text-to-video, alibaba/wan-2.6/image-to-video-flash, alibaba/wan-2.6/reference-to-video-flash, and more. Each variant has its own playground page and pricing.
Can I use Wan 2.6 outputs commercially?
Commercial usage rights follow the Alibaba model license. Most Alibaba models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Wan 2.6 on WaveSpeedAI instead of going direct?
One API key + one billing account across Wan 2.6 AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below Alibaba's direct API.
About Alibaba
The team behind Wan 2.6 and the broader Alibaba model lineup on WaveSpeedAI.
Alibaba's Tongyi Lab produces the Wan family of video models and the Qwen family of LLMs. Wan is notable for being released with open weights, broad variant coverage (text-to-video, image-to-video, reference-to-video, video-edit, video-extend, image-edit, text-to-image), and consistent strength on motion stability and prompt adherence across multilingual prompts.
Start building with Wan 2.6 on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from Alibaba and every other provider.