Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openclaw.ai/llms.txt

Use this file to discover all available pages before exploring further.

OpenClaw ships a bundled alibaba plugin that registers a video-generation provider for Wan models on Alibaba Model Studio (the international name for DashScope). The plugin is enabled by default; you only need to set an API key.
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

Use onboarding to store the key against the alibaba provider:
openclaw onboard --auth-choice alibaba-model-studio-api-key
Or pass the key directly during install/onboarding:
openclaw onboard --alibaba-model-studio-api-key <your-key>
Or export any 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 should include all five bundled Wan models. If MODELSTUDIO_API_KEY is unresolved, 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 to drive the dedicated Wan video surface; use qwen/... ids when you want Qwen’s chat, embedding, or media-understanding surface.

​
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

The bundled provider mirrors DashScope’s Wan video API caps. 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
When a request omits durationSeconds, the provider sends 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. Local file paths are not accepted by DashScope’s reference modes; 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, set:
{
  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 to drive 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 because the auth env var list intentionally overlaps; you do not need to onboard each plugin separately.

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.