Reference
A

Wan 2.7

Wan 2.7, a video model from Alibaba Cloud.
videoModelOverride: { model: "wan2.7-video" }
Wan·served viaAlibaba Cloud·Released February 2026
Pricing
List price
$0.05-$0.15/second
Per generation
$0.075
Per generation
$0.037
Per generation
$0.050
Per generation
$0.025
Per generation
$0.075
Per generation
$0.037
Per generation
$0.050
Per generation
$0.025
Per generation
$0.15
Per generation
$0.10
Per generation
$0.15
Per generation
$0.10
Specifications
Context window
2,000 tokens
Aspect ratios
3
Released
February 2026
Parameters
Model options, passed in videoModelOverride.config.
ParameterTypeDefaultRange / options
$modeSelecttext-to-videotext-to-videoimage-to-videoreference-to-videovideo-edit
image
Image used as the first frame of the generated video.
Image URL
video
The video to edit. Describe your edits in the prompt using natural language instructions. Supports both localized and global edits.
Video URL
reference_images
Provide reference images of people or objects to keep their appearance (and voice) consistent in the generated video. Reference them as "Character 1", "Character 2", etc. in the prompt. Supports multi-character joint performances.
Image URLs
edit_reference_images
Optionally provide reference images to seamlessly replace elements in the video.
Image URLs
resolutionSelect720P720P1080P
ratioSelect16:916:99:16
durationSelect551015
audio
Generate synchronized audio including dialogue, vocals, and sound effects alongside the video.
Booleanfalse
shot_type
Multi-shot uses intelligent shot scheduling to generate multi-shot narrative videos with consistent subjects, scenes, and atmosphere.
Selectsinglesinglemulti
prompt_extend
Automatically rewrite and expand the prompt for improved output quality.
Booleantrue
Use this model
await mindstudio.generateVideo({
  prompt: "...",
  videoModelOverride: {
    model: "wan2.7-video",
    config: {
      resolution: "720P",
      ratio: "16:9",
    },
  },
});