Wan 2.7 Video API — Text, Image & Reference Video Generation
One Wan 2.7 Video API endpoint is a text to video API, an image to video API, a reference to video API, and a video editing API at once. The Alibaba Wan video model auto-routes by request shape, renders 720P or 1080P, and bills per second.
Price
Per second$0.073/ 1 second
Per second$0.1206/ 1 second
01playground
InputsPOST /api/v1/videos/generations
Up to 5000 characters
Up to 500 characters · optional
Public URL · optional
Default 16:9
720P · 1080P · default 1080P
5
2 to 15 seconds · default 5
Default on
Default off
Integer · optional
Outputidle
try one of these prompts
02use cases
What you can build
Real workflows powered by this model.
01/case
Turn a prompt or a still image into video
Send a prompt to use it as a text to video API, or add an image to use it as an image to video API. The Wan 2.7 Video API auto-detects the request shape, so a single endpoint covers wan2.7 video text-to-video and image-to-video without a separate mode flag. Pick 720P or 1080P and a duration from 2 to 15 seconds.
Generate a clip02/case
Drive new characters with reference clips
As a reference to video API, the Wan 2.7 Video API takes reference images and reference videos so the output keeps your subjects while following a referenced performance. Add reference voices to carry per-subject audio. It is the same Wan 2.7 Video API call — just a different set of inputs.
03/case
Edit an existing video in place
As a video editing API, the Wan 2.7 Video API takes a source video to the video-editing mode and re-renders it against your prompt, while the audio_setting controls whether the original soundtrack is kept. One model is your text to video API, image to video API, reference to video API, and video editing API in a single integration.
03pricing
Pricing
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
| Category | Unit | Price |
|---|---|---|
| 720P | ||
| Per second | 1 second | $0.07304000000000001 74 credits |
| 1080P | ||
| Per second | 1 second | $0.12056000000000001 121 credits |
05why
Why reAPI
01
One model, every mode
The Wan 2.7 Video API routes by request shape into text-to-video, image-to-video, reference-to-video, and video editing. You learn one Wan 2.7 Video API endpoint and one parameter set instead of stitching four separate models together — one text to video API that doubles as an image to video API.
02
Reference-driven subject control
Reference images, reference videos, and reference voices let the Wan 2.7 Video API keep your subjects consistent while following a referenced performance — useful for avatars, recurring characters, and product shots the Wan 2.7 Video API renders on demand.
03
Pay for the seconds you render
Billing is per second of video, scaled by resolution. Choose 720P or 1080P, set the duration, and the cost is proportional. Failed jobs refund automatically, so a rejected Wan 2.7 Video API request never costs credits.
06vs
Wan 2.7 Video vs Veo 3
Both generate video from text and images. The Wan 2.7 Video API folds text-to-video, image-to-video, reference-to-video, and video editing into one endpoint with per-second pricing. Here is how the two compare on publicly documented behavior.
Capability
Wan 2.7 Video on reAPI
Veo 3
Modes
One endpoint auto-routes to text-to-video, image-to-video, reference-to-video, and video editing.
Text-to-video and image-to-video; no documented in-model video editing or multi-subject reference mode.
Resolutions
720P and 1080P, selectable per request.
Up to 1080P depending on tier.
Durations
2 to 15 seconds for base modes; reference and editing modes cap shorter.
Fixed short clips, typically around 8 seconds.
Reference-to-video
Reference images, videos, and per-subject voices keep subjects consistent across a referenced performance.
No documented multi-reference subject-consistency mode.
Video editing
Pass a source video to re-render it against a prompt, with audio_setting controlling the soundtrack.
No documented in-model video-editing mode.
Pricing model
Per second of video, scaled by resolution; pay-as-you-go credits with automatic refunds on failure.
Per-second pricing tied to plan and tier.
Comparison reflects publicly documented behavior at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.
07quickstart
Ship the Wan 2.7 Video API in three steps
- step 01
Create an API key
Sign up and grab a key from the dashboard. Free credits cover your first Wan 2.7 Video API calls — no card required.
Open - step 02
Submit a video task
POST to /api/v1/videos/generations with model = wan2.7-video plus a prompt or media input, a resolution, and a duration. The Wan 2.7 Video API returns a task ID immediately.
Open - step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. Read the generated clip from output.video_urls and ship it.
Open
08faq
Frequently asked questions
Common questions about this model.
The Wan 2.7 Video API is a single endpoint over the Alibaba Wan video model, wan2.7 video. One umbrella model auto-routes by request shape into text-to-video, image-to-video, reference-to-video, and video editing, so the same Wan 2.7 Video API call handles every mode.
Related models
Explore more models in the same category.
Kuaishou
Kling Motion Control
Reference image plus reference video — controllable motion transfer in one Kling Motion Control API call.
From $0.063 per second
PixVerse
Pixverse v6
Text, image, keyframe, reference, and extend video in one Pixverse v6 API call.
From $0.019 per second
—
Enhance Video 1.0
Video enhancer API — 4K upscale, denoise, scene presets, frame interpolation in one async endpoint.
From $0.003 per second
10api reference
docs/api/wan-2-7-video
curl -X POST https://reapi.ai/api/v1/videos/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan2.7-video",
"prompt": "a paper boat drifting down a rain-soaked street at dusk",
"resolution": "1080P",
"duration": 5
}'start building
Ready to ship?
Try it in the playground or grab an API key to integrate now.