Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Configure OpenClaw (including historical Moltbot/Clawdbot paths) to use Alibaba Cloud Model Studio through a strict interactive flow. The first required step is asking whether the user can run terminal commands now; use that answer to choose env-var mode (preferred) or inline mode before collecting site/key details. Use this skill when a user asks to add, switch, or repair Alibaba Cloud/Qwen provider configuration in OpenClaw.
Configure OpenClaw (including historical Moltbot/Clawdbot paths) to use Alibaba Cloud Model Studio through a strict interactive flow. The first required step is asking whether the user can run terminal commands now; use that answer to choose env-var mode (preferred) or inline mode before collecting site/key details. Use this skill when a user asks to add, switch, or repair Alibaba Cloud/Qwen provider configuration in OpenClaw.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Use this skill to configure Alibaba Cloud Bailian as an OpenClaw model provider with minimal manual editing. Supports both Pay-As-You-Go (ๆ้ไป่ดน) and Coding Plan (่ฎข้ ๅถ) subscription types.
Provider: bailian (not "balian" - typo fixed!)
Plan TypeSiteBase URLPay-As-You-GoChina (CN)https://dashscope.aliyuncs.com/compatible-mode/v1Pay-As-You-GoInternational (INTL)https://dashscope-intl.aliyuncs.com/compatible-mode/v1Pay-As-You-GoUS (US)https://dashscope-us.aliyuncs.com/compatible-mode/v1Coding PlanChina (CN)https://coding.dashscope.aliyuncs.com/v1Coding PlanInternational (INTL)https://coding-intl.dashscope.aliyuncs.com/v1
Qwen-Max (Best Performance): qwen-max qwen-max-2025-01-25 Qwen-Plus (Balanced): qwen-plus qwen-plus-2025-01-15 Qwen-Flash (Fast & Cost-Effective): qwen-flash qwen-flash-2025-01-15 Qwen-Coder (Code Specialist): qwen3-coder-plus qwen3-coder-next qwen2.5-coder-32b-instruct
qwen3.5-plus qwen3-max-2026-01-23
MiniMax-M2.5 (MiniMax) glm-5 / glm-4.7 (ๆบ่ฐฑ AI) kimi-k2.5 (ๆไนๆ้ข) Total: Pay-As-You-Go: 11 models (4 flagship series + 2 latest Qwen) Coding Plan: 15 models (Pay-As-You-Go + 4 third-party exclusive)
Confirm plan type: Pay-As-You-Go or Coding Plan Select site: Based on plan type (3 options for Pay-As-You-Go, 2 for Coding Plan) Run interactive script to collect: API key (with validation) API key storage mode (env-var recommended or inline) Primary model selection Whether to set as default model Validate API key against selected site before config write Backup existing config before modification Update config with provider, models, and defaults Validate JSON and report final status
Execute: python3 scripts/alibaba_cloud_model_setup.py Optional flags for non-interactive use: python3 scripts/alibaba_cloud_model_setup.py \ --plan-type coding \ --site cn \ --api-key-source env \ --env-var DASHSCOPE_API_KEY \ --models qwen3.5-plus,qwen3-max-2026-01-23,qwen3-coder-plus \ --model qwen3.5-plus \ --set-default List available models (no config write): python3 scripts/alibaba_cloud_model_setup.py \ --plan-type coding \ --site cn \ --list-models \ --non-interactive
Always run python3 scripts/alibaba_cloud_model_setup.py for configuration changes. Never edit ~/.openclaw/openclaw.json manually when this skill is used. Always validate API key before writing config. Always create backup before overwriting existing config. In environment-variable mode, never proceed to config write unless env detection succeeds.
Detect config path in this order: ~/.openclaw/openclaw.json ~/.moltbot/moltbot.json ~/.clawdbot/clawdbot.json If none exists, create ~/.openclaw/openclaw.json Write provider bailian with OpenAI-compatible API mode Create a timestamped backup before overwriting an existing file Preserve unrelated config sections Set models.mode to merge to preserve other providers
After configuration: Confirm JSON is valid by running python3 -m json.tool <config-path>. Ensure models.providers.bailian.baseUrl matches site selection. Ensure models.providers.bailian.models contains expected model IDs. Ensure agents.defaults.model.primary is bailian/<model-id> when default is enabled. Start dashboard (openclaw dashboard) or TUI (openclaw tui) and verify model call succeeds.
{ "models": { "mode": "merge", "providers": { "bailian": { "baseUrl": "https://coding.dashscope.aliyuncs.com/v1", "apiKey": "YOUR_API_KEY", "api": "openai-completions", "models": [ { "id": "qwen3.5-plus", "name": "Qwen3.5 Plus", "reasoning": false, "input": ["text", "image"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 1000000, "maxTokens": 65536 }, { "id": "qwen3-max-2026-01-23", "name": "Qwen3 Max 2026-01-23", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 262144, "maxTokens": 65536 }, { "id": "qwen3-coder-next", "name": "Qwen3 Coder Next", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 262144, "maxTokens": 65536 }, { "id": "qwen3-coder-plus", "name": "Qwen3 Coder Plus", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 1000000, "maxTokens": 65536 }, { "id": "MiniMax-M2.5", "name": "MiniMax M2.5", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 204800, "maxTokens": 131072 }, { "id": "glm-5", "name": "GLM-5", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 202752, "maxTokens": 16384 }, { "id": "glm-4.7", "name": "GLM-4.7", "reasoning": false, "input": ["text"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 202752, "maxTokens": 16384 }, { "id": "kimi-k2.5", "name": "Kimi K2.5", "reasoning": false, "input": ["text", "image"], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 262144, "maxTokens": 32768 } ] } } }, "agents": { "defaults": { "model": { "primary": "bailian/qwen3.5-plus" }, "models": { "bailian/qwen3.5-plus": {}, "bailian/qwen3-max-2026-01-23": {}, "bailian/qwen3-coder-next": {}, "bailian/qwen3-coder-plus": {}, "bailian/MiniMax-M2.5": {}, "bailian/glm-5": {}, "bailian/glm-4.7": {}, "bailian/kimi-k2.5": {} } } } }
Endpoint and field conventions: references/openclaw_alibaba_cloud.md Version: 0.1.4 Updated: 2026-03-02 Changes: Fixed provider name typo (balian โ bailian), added Coding Plan support, 5 site options, 11 models for Pay-As-You-Go (flagship + latest Qwen), 15 models for Coding Plan (+4 third-party exclusive)
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.