Skip to main content
The bundled alibaba plugin registers a video-generation provider for Wan models on Alibaba Model Studio (the international name for DashScope). It is enabled by default; only an API key is needed.
PropertyValue
Provider idalibaba
Pluginbundled, enabledByDefault: true
Auth env varsMODELSTUDIO_API_KEY → DASHSCOPE_API_KEY → QWEN_API_KEY (first match wins)
Onboarding flag--auth-choice alibaba-model-studio-api-key
Direct CLI flag--alibaba-model-studio-api-key <key>
Default modelalibaba/wan2.6-t2v
Default base URLhttps://dashscope-intl.aliyuncs.com

​
Getting started

1

Set an API key

Store the key against the alibaba provider through onboarding:
openclaw onboard --auth-choice alibaba-model-studio-api-key
Or pass the key directly:
openclaw onboard --alibaba-model-studio-api-key <your-key>
Or export one of the accepted env vars before starting the Gateway:
export MODELSTUDIO_API_KEY=sk-...
# or DASHSCOPE_API_KEY=...
# or QWEN_API_KEY=...
2

Set a default video model

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "alibaba/wan2.6-t2v",
      },
    },
  },
}
3

Verify the provider is configured

openclaw models list --provider alibaba
The list includes all five bundled Wan models. If MODELSTUDIO_API_KEY cannot be resolved, openclaw models status --json reports the missing credential under auth.unusableProfiles.
The Alibaba plugin and the Qwen plugin both authenticate against DashScope and accept overlapping env vars. Use alibaba/... model ids for the dedicated Wan video surface; use qwen/... ids for Qwen chat, embedding, or media-understanding.

​
Built-in Wan models

Model refMode
alibaba/wan2.6-t2vText-to-video (default)
alibaba/wan2.6-i2vImage-to-video
alibaba/wan2.6-r2vReference-to-video
alibaba/wan2.6-r2v-flashReference-to-video (fast)
alibaba/wan2.7-r2vReference-to-video

​
Capabilities and limits

All three modes share the same per-request video count and duration cap; only the input shape differs.
ModeMax output videosMax input imagesMax input videosMax durationSupported controls
Text-to-video1n/an/a10 ssize, aspectRatio, resolution, audio, watermark
Image-to-video11n/a10 ssize, aspectRatio, resolution, audio, watermark
Reference-to-video1n/a410 ssize, aspectRatio, resolution, audio, watermark
A request that omits durationSeconds gets DashScope’s accepted default of 5 seconds. Set durationSeconds explicitly on the video generation tool to extend up to 10 s.
Reference image and video inputs must be remote http(s) URLs; DashScope’s reference modes reject local file paths. Upload to object storage first, or use the media tool flow that already produces a public URL.

​
Advanced configuration

The provider defaults to the international DashScope endpoint. To target the China-region endpoint:
{
  models: {
    providers: {
      alibaba: {
        baseUrl: "https://dashscope.aliyuncs.com",
      },
    },
  },
}
The provider strips trailing slashes before constructing AIGC task URLs.
OpenClaw resolves the Alibaba API key from environment variables in this order, taking the first non-empty value:
  1. MODELSTUDIO_API_KEY
  2. DASHSCOPE_API_KEY
  3. QWEN_API_KEY
Configured auth.profiles entries (set via openclaw models auth login) override env-var resolution. See Auth profiles in the models FAQ for profile rotation, cooldown, and override mechanics.
Both bundled plugins talk to DashScope and accept overlapping API keys. Use:
  • alibaba/wan*.* ids for the dedicated Wan video provider documented on this page.
  • qwen/* ids for Qwen chat, embedding, and media understanding (see Qwen).
Setting MODELSTUDIO_API_KEY once authenticates both plugins, since the auth env var list intentionally overlaps; onboarding each plugin separately is not required.

Video generation

Shared video tool parameters and provider selection.

Qwen

Qwen chat, embedding, and media-understanding setup on the same DashScope auth.

Configuration reference

Agent defaults and model configuration.

Models FAQ

Auth profiles, switching models, and resolving “no profile” errors.