Qwen

Qwen Cloud is an official external OpenClaw provider plugin with canonical id qwen. It targets Qwen Cloud / Alibaba DashScope Standard and Coding Plan endpoints, exposes Token Plan as qwen-token-plan, keeps modelstudio as a compatibility alias, independently owns Alibaba's documented bailian-token-plan custom-provider id, and exposes the Qwen Portal token flow as qwen-oauth.

Install plugin

qwen ships as an official external plugin, not bundled with core. Install it and restart Gateway:

openclaw plugins install @openclaw/qwen-provideropenclaw gateway restart

Getting started

Choose your plan type and follow the setup steps.

openclaw onboard --auth-choice qwen-api-key

openclaw onboard --auth-choice qwen-api-key-cn

{  agents: {    defaults: {      model: { primary: "qwen/qwen3.5-plus" },    },  },}

openclaw models list --provider qwen

openclaw onboard --auth-choice qwen-standard-api-key

openclaw onboard --auth-choice qwen-standard-api-key-cn

{  agents: {    defaults: {      model: { primary: "qwen/qwen3.5-plus" },    },  },}

openclaw models list --provider qwen

openclaw onboard --auth-choice qwen-token-plan

openclaw onboard --auth-choice qwen-token-plan-cn

openclaw models list --provider qwen-token-planopenclaw agent --model qwen-token-plan/qwen3.7-plus --message "Reply with: token plan ready"

openclaw onboard --auth-choice qwen-oauth

{  agents: {    defaults: {      model: { primary: "qwen-oauth/qwen3.5-plus" },    },  },}

openclaw models list --provider qwen-oauth

Plan types and endpoints

The provider auto-selects the endpoint based on your auth choice. Canonical choices use the qwen-* family; modelstudio-* remains compatibility-only. Override with a custom baseUrl in config.

Built-in catalog

OpenClaw ships this Qwen static catalog. The catalog is endpoint-aware: Coding Plan configs omit models that only work on the Standard endpoint.

Token Plan catalog

Token Plan uses a separate exact-string allowlist. Image-generation-only plan models are not included here because they use different APIs.

Thinking controls

qwen3.7-max, qwen3.7-plus, qwen3.6-flash, and qwen3.6-plus are reasoning-enabled in the built-in catalog. For reasoning models on the qwen family, the provider maps OpenClaw thinking levels to DashScope's top-level enable_thinking request flag: disabled thinking sends enable_thinking: false, any other level sends enable_thinking: true. Custom models can opt into an alternate chat-template thinking payload by setting compat.thinkingFormat: "qwen-chat-template" on the model entry.

Token Plan models are also marked reasoning-capable. kimi-k2.7-code and MiniMax-M2.5 are thinking-only, so OpenClaw keeps thinking enabled even when the session requests /think off. DeepSeek V4 maps minimal through high to the service's high effort and maps xhigh or max to max. GLM 5.2 accepts the full minimal through max range; GLM 5.1 and GLM 5 accept through xhigh, and all three default to high. Other hybrid models follow the requested on/off state.

Multimodal add-ons

The qwen plugin exposes multimodal capabilities on the Standard DashScope endpoints only, not the Coding Plan endpoints:

• Image and video understanding via qwen-vl-max-latest
• Wan video generation via wan2.6-t2v (default), wan2.6-i2v, wan2.6-r2v, wan2.6-r2v-flash, wan2.7-r2v

Media understanding is auto-resolved from the configured Qwen auth; no extra config is needed. Make sure you are on a Standard (pay-as-you-go) endpoint for media understanding to work.

To make Qwen the default video provider:

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

Video-generation limits: 1 output video per request, up to 1 input image (image-to-video), up to 4 input videos (video-to-video), max 10 seconds duration. Supports size, aspectRatio, resolution, audio, and watermark. Reference image/video inputs require remote http(s) URLs; local file paths are rejected up front because the DashScope video endpoint does not accept uploaded local buffers for those references.

Advanced configuration

Related