Wan 2.7 API

About the Wan 2.7 API

What Wan 2.7 does, how it fits in the Alibaba model lineup, and why teams reach for it.

All Wan 2.7 API endpoints

9 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Text To Image

WAN 2.7 Text-to-Image generates high-quality images from text prompts with thinking mode for enhanced image quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-imagefrom $0.030

Text To Image Pro

WAN 2.7 Text-to-Image Pro generates high-quality images up to 4K from text prompts with thinking mode for enhanced image quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-imagefrom $0.075

Video Extend

WAN 2.7 Video Extend extends existing videos with optional last frame control and audio support, supporting 720p/1080p output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

video-extendfrom $0.50

Reference To Video

WAN 2.7 Reference-to-Video turns character, prop, or scene references from images or videos 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-to-videofrom $0.50

Text To Video

WAN 2.7 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.

text-to-videofrom $0.50

Image Edit Pro

WAN 2.7 Image Edit Pro performs prompt-driven image editing with multi-image reference support and up to 2K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-imagefrom $0.075

Video Edit

WAN 2.7 Video Edit performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

video-to-videofrom $0.50

Image Edit

WAN 2.7 Image Edit performs prompt-driven image editing with support for multiple-image references. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-imagefrom $0.030

Image To Video

WAN 2.7 converts images into videos (720p/1080p) with optional audio, supporting first and last frame control. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

image-to-videofrom $0.50

See Wan 2.7 in action

Real outputs generated by the Wan 2.7 API. Hover any video to preview, click to open the full-size viewer.

Close-up portrait of a woman pressing her palm against a rain-soaked window at night, shot from outside. Heavy rain streaks distort her face through the glass, neon signs from the street below cast fragmented magenta and cyan reflections across her skin. Camera slowly pushes in at 0.3x speed. Shallow depth of field, bokeh rain drops, dual-exposure ghosting of her reflection overlapping her face. Cinematic 4K, anamorphic lens flare, 24fps.

Extreme close-up portrait, woman's face in profile against golden hour sun, shot with 85mm f/1.2. Sun positioned directly behind her head creating a blazing rim light halo. Individual strands of hair catch the light and glow translucent amber. A gentle breeze causes hair to drift across her cheek in slow motion. Skin subsurface scattering visible on ear and nose tip. Dust particles float through the backlit air. Hyper-realistic, 120fps slow motion playback at 24fps, anamorphic 2.39:1.

Portrait of a woman aging from 20 to 80 and back to 20, seamless morphing over 10 seconds. Shot in style of 1960s 16mm film with authentic gate weave, film grain, occasional splice marks and light leaks. The background remains constant — a sun-drenched window in a Paris apartment — while only her face transforms. Color grade shifts from saturated Kodachrome warmth in youth to desaturated, slightly faded tones in age, then back. No CGI aesthetic — must feel like archival film footage.

The man was singing, and passersby applauded and gave him some change.

The characters in Video 1 and Video 2 are sitting in front of the TV and playing video games together.

Change the motorcycle's color to blue.

replace the main subject with a blonde woman

Close-up portrait of a model whose face is partially covered in flowing liquid metal or an iridescent, second-skin-like substance. She has otherworldly, light purple eyes and stares directly into the camera. The background is completely blurred out, leaving only a soft halo of light. The lighting is even and ethereal, as if from a bioluminescent source. Inspired by the style of Nick Knight, the image emphasizes surreal textures and subtle color gradients, exceptionally sharp, with breathtaking detail, 16K.\n

How to use the Wan 2.7 API

Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.

1. 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. 2

   Submit a prediction

   POST your input as JSON to https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/text-to-video. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.

3. 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. 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 2.7 variant you called.

What you can build with Wan 2.7

Common workflows developers and creators use the Wan 2.7 API for.

Tips for prompting Wan 2.7

Practical advice for getting better outputs from Wan 2.7 — drawn from the patterns that work across video models in production pipelines.

Wan 2.7 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).

Call the Wan 2.7 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.

# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/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].

// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY

const result = await client.run("alibaba/wan-2.7/text-to-video", {});
console.log(result.outputs[0]); // → URL of the generated output

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "alibaba/wan-2.7/text-to-video",
    {}
)
print(output["outputs"][0])  # → URL of the generated output

Wan 2.7 vs alternatives

When to pick Wan 2.7 over similar models on WaveSpeedAI.

Wan 2.7 API — Frequently asked questions

Pricing, license, integration — common questions about running Wan 2.7 on WaveSpeedAI.

About Alibaba

The team behind Wan 2.7 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, full-modality input support (text, image, video, and audio references in a single generation), and consistent strength on physics, motion, and multilingual prompts.

Related model APIs on WaveSpeedAI

Other AI APIs from Alibaba and the rest of the video model lineup — one API key, one billing account.