OpenClaw integrates with third-party model providers, including Model Studio Token Plan, MiniMax, Tencent Cloud, Zhipu, and DeepSeek. This topic covers integration steps, parameter configurations, and specific considerations for each provider.-Simple Application Server(SAS)-阿里云帮助中心

OpenClaw supports Alibaba Cloud Model Studio's Coding Plan by default. To integrate model plans from other providers, modify the configuration file. This document demonstrates how to integrate the following seven plans and models: Model Studio Token Plan Team Edition, MiniMax Token Plan, Zhipu GLM Coding Plan, Tencent Cloud Token Plan, Coding Plan, DeepSeek V4, and Volcengine Agent Plan.

Provider onboarding

Bailian token plan team

Access the terminal: Log in to the Simple Application Server console, find the card for your target server, and click Remote Connection. In the Connect with One-click on Workbench area, click Log on Now.
Make sure your account is subscribed to the Token Plan Team Edition.

Modify the configuration file: Run the following command in the terminal.

vim ~/.openclaw/openclaw.json

Add the following configuration to models.providers. Replace <YOUR_API_KEY> with your API key:

"models": {
  "mode": "merge",
  "providers": {
    "bailian-token-plan": {
      "baseUrl": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
      "apiKey": "YOUR_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "qwen3.7-max",
          "name": "qwen3.7-max",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 1000000,
          "maxTokens": 65536,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "qwen3.6-plus",
          "name": "qwen3.6-plus",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 1000000,
          "maxTokens": 65536,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "qwen3.6-flash",
          "name": "qwen3.6-flash",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 1000000,
          "maxTokens": 32768,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "deepseek-v4-pro",
          "name": "deepseek-v4-pro",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 163840,
          "maxTokens": 32768,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "deepseek-v4-flash",
          "name": "deepseek-v4-flash",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 163840,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "deepseek-v3.2",
          "name": "deepseek-v3.2",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 163840,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "kimi-k2.6",
          "name": "kimi-k2.6",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 262144,
          "maxTokens": 32768,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "kimi-k2.5",
          "name": "kimi-k2.5",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 262144,
          "maxTokens": 32768,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "glm-5.1",
          "name": "glm-5.1",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 202752,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "glm-5",
          "name": "glm-5",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 202752,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "compat": { "thinkingFormat": "qwen" }
        },
        {
          "id": "MiniMax-M2.5",
          "name": "MiniMax-M2.5",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 196608,
          "maxTokens": 32768,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    }
  }
}

In openclaw.json, modify the agents.defaults section to include the following model list. By default, the primary model is qwen3.6-plus, but you can change it to any other supported model:

"agents": {
  "defaults": {
    "model": {
      "primary": "bailian-token-plan/qwen3.6-plus"
    },
    "models": {
      "bailian-token-plan/qwen3.7-max": {},
      "bailian-token-plan/qwen3.6-plus": {},
      "bailian-token-plan/qwen3.6-flash": {},
      "bailian-token-plan/deepseek-v4-pro": {},
      "bailian-token-plan/deepseek-v4-flash": {},
      "bailian-token-plan/deepseek-v3.2": {},
      "bailian-token-plan/kimi-k2.6": {},
      "bailian-token-plan/kimi-k2.5": {},
      "bailian-token-plan/glm-5.1": {},
      "bailian-token-plan/glm-5": {},
      "bailian-token-plan/MiniMax-M2.5": {}
    }
  }
}

Restart the service to apply the configuration: After saving the file, run the following command to restart OpenClaw.
```
openclaw gateway restart
```

MiniMax token plan

Log in to the Simple Application Server console, find the card for your target server, and click Remote Connection. In the Connect with One-click on Workbench section, click Log on Now.
Make sure your account is subscribed to the MiniMax Token Plan.

Run openclaw configure in the terminal and make the following selections:

Where will the Gateway run?     → Local (this machine)
Select sections to configure    → Model
Model/auth provider             → MiniMax
Auth method                     → MiniMax CN — API Key (minimaxi.com)   # For international users, select MiniMax Global
Enter API Key                   → Paste your Token Plan API key
Default model                   → Keep the default (MiniMax-M2.7)
Select sections to configure    → Continue

Zhipu GLM coding plan

Log in to the Simple Application Server console, find the card for your target server, and click Remote Connection. Under the Connect with One-click on Workbench section, click Log on Now.
Make sure your account is subscribed to the Zhipu GLM Coding Plan.

Run openclaw config in the terminal and make the following selections:

Where will the Gateway run?                                  → Local (this machine)
Select sections to configure                                 → Model
Model/auth provider                                          → Z.AI
Z.AI auth method                                             → Coding-Plan-CN
Enter API Key                                                → Paste the Zhipu AI API Key from the previous step
Select model                                                 → zai/glm-5.1
Select sections to configure                                 → Continue

Tencent Cloud Token Plan

After obtaining your API key, modify the configuration file using one of the following methods:

WebUI

In the OpenClaw WebUI, navigate to Configuration > Raw from the left-side menu bar. In the openclaw.json configuration, update the models.providers section. Replace <USER_API_KEY> with your API key:

"models": {
  "mode": "merge",
  "providers": {
    "tencent-token-plan": {
      "baseUrl": "https://api.lkeap.cloud.tencent.com/plan/v3",
      "apiKey": "USER_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "tc-code-latest",
          "name": "Auto",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "hunyuan-2.0-instruct",
          "name": "Tencent HY 2.0 Instruct",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 16000
        },
        {
          "id": "hunyuan-2.0-thinking",
          "name": "Tencent HY 2.0 Think",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-t1",
          "name": "Hunyuan-T1",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 64000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-turbos",
          "name": "hunyuan-turbos",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 32000,
          "maxTokens": 16000
        },
        {
          "id": "minimax-m2.5",
          "name": "MiniMax-M2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "kimi-k2.5",
          "name": "Kimi-K2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 262144,
          "maxTokens": 32768
        },
        {
          "id": "glm-5",
          "name": "GLM-5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 202752,
          "maxTokens": 16384
        }
      ]
    }
  }
}

In the openclaw.json configuration, modify agents.defaults and add the model list information (the primary field defaults to glm-5 and can be changed to any of the models supported in models):

"agents": {
  "defaults": {
    "model": {
      "primary": "tencent-token-plan/glm-5"
    },
    "models": {
      "tencent-token-plan/tc-code-latest": {},
      "tencent-token-plan/hunyuan-2.0-instruct": {},
      "tencent-token-plan/hunyuan-2.0-thinking": {},
      "tencent-token-plan/hunyuan-t1": {},
      "tencent-token-plan/hunyuan-turbos": {},
      "tencent-token-plan/minimax-m2.5": {},
      "tencent-token-plan/kimi-k2.5": {},
      "tencent-token-plan/glm-5": {}
    }
  }
}

After making the changes, click Save and then Update to apply them.

CLI

Log in to the terminal without a password: Log in to the Simple Application Server console, find the card for your target server, and click Remote Connection. In the Connect with One-click on Workbench area, click Log on Now.

Modify the configuration file: Run the following command to edit the configuration file.

vim ~/.openclaw/openclaw.json

In the models.providers section, update the configuration as follows (replace <USER_API_KEY> with your API key):

"models": {
  "mode": "merge",
  "providers": {
    "tencent-token-plan": {
      "baseUrl": "https://api.lkeap.cloud.tencent.com/plan/v3",
      "apiKey": "USER_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "tc-code-latest",
          "name": "Auto",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "hunyuan-2.0-instruct",
          "name": "Tencent HY 2.0 Instruct",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 16000
        },
        {
          "id": "hunyuan-2.0-thinking",
          "name": "Tencent HY 2.0 Think",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-t1",
          "name": "Hunyuan-T1",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 64000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-turbos",
          "name": "hunyuan-turbos",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 32000,
          "maxTokens": 16000
        },
        {
          "id": "minimax-m2.5",
          "name": "MiniMax-M2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "kimi-k2.5",
          "name": "Kimi-K2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 262144,
          "maxTokens": 32768
        },
        {
          "id": "glm-5",
          "name": "GLM-5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 202752,
          "maxTokens": 16384
        }
      ]
    }
  }
}

In openclaw.json, modify agents.defaults to add the model list information (the primary field defaults to glm-5, and can be changed to any model supported in models):

"agents": {
  "defaults": {
    "model": {
      "primary": "tencent-token-plan/glm-5"
    },
    "models": {
      "tencent-token-plan/tc-code-latest": {},
      "tencent-token-plan/hunyuan-2.0-instruct": {},
      "tencent-token-plan/hunyuan-2.0-thinking": {},
      "tencent-token-plan/hunyuan-t1": {},
      "tencent-token-plan/hunyuan-turbos": {},
      "tencent-token-plan/minimax-m2.5": {},
      "tencent-token-plan/kimi-k2.5": {},
      "tencent-token-plan/glm-5": {}
    }
  }
}

Restart the service: After saving the file, run the following command to restart OpenClaw.
```
openclaw gateway restart
```

Tencent Cloud coding plan

After you get the API key, choose one of the following methods to modify the configuration file:

WebUI

Go to the OpenClaw WebUI, select Configuration > Raw from the left menu bar, and in the openclaw.json configuration, modify the models.providers setting (replace <USER_API_KEY> with the API key from the previous step):

"models": {
  "mode": "merge",
  "providers": {
    "tencent-coding-plan": {
      "baseUrl": "https://api.lkeap.cloud.tencent.com/coding/v3",
      "apiKey": "USER_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "tc-code-latest",
          "name": "Auto",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "hunyuan-2.0-instruct",
          "name": "Tencent HY 2.0 Instruct",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 16000
        },
        {
          "id": "hunyuan-2.0-thinking",
          "name": "Tencent HY 2.0 Think",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-t1",
          "name": "Hunyuan-T1",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 64000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-turbos",
          "name": "hunyuan-turbos",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 32000,
          "maxTokens": 16000
        },
        {
          "id": "minimax-m2.5",
          "name": "MiniMax-M2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "kimi-k2.5",
          "name": "Kimi-K2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 262144,
          "maxTokens": 32768
        },
        {
          "id": "glm-5",
          "name": "GLM-5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 202752,
          "maxTokens": 16384
        }
      ]
    }
  }
}

In the openclaw.json configuration, modify agents.defaults to add the model list information (the primary field defaults to glm-5 and can be changed to any model supported in the models list):

"agents": {
  "defaults": {
    "model": {
      "primary": "tencent-coding-plan/glm-5"
    },
    "models": {
      "tencent-coding-plan/tc-code-latest": {},
      "tencent-coding-plan/hunyuan-2.0-instruct": {},
      "tencent-coding-plan/hunyuan-2.0-thinking": {},
      "tencent-coding-plan/hunyuan-t1": {},
      "tencent-coding-plan/hunyuan-turbos": {},
      "tencent-coding-plan/minimax-m2.5": {},
      "tencent-coding-plan/kimi-k2.5": {},
      "tencent-coding-plan/glm-5": {}
    }
  }
}

Click Save, then click Update to apply the changes.

Terminal

Passwordless terminal login: Log in to the Lighthouse console, find your server, and click Remote Connection. In the Connect with One-click on Workbench area, click Log on Now.

Modify the configuration file: Run the following command in the terminal.

vim ~/.openclaw/openclaw.json

In models.providers, modify the following configuration (replace <USER_API_KEY> with the API Key from the previous step):

"models": {
  "mode": "merge",
  "providers": {
    "tencent-coding-plan": {
      "baseUrl": "https://api.lkeap.cloud.tencent.com/coding/v3",
      "apiKey": "USER_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "tc-code-latest",
          "name": "Auto",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "hunyuan-2.0-instruct",
          "name": "Tencent HY 2.0 Instruct",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 16000
        },
        {
          "id": "hunyuan-2.0-thinking",
          "name": "Tencent HY 2.0 Think",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 128000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-t1",
          "name": "Hunyuan-T1",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 64000,
          "maxTokens": 32000
        },
        {
          "id": "hunyuan-turbos",
          "name": "hunyuan-turbos",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 32000,
          "maxTokens": 16000
        },
        {
          "id": "minimax-m2.5",
          "name": "MiniMax-M2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 196608,
          "maxTokens": 32768
        },
        {
          "id": "kimi-k2.5",
          "name": "Kimi-K2.5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 262144,
          "maxTokens": 32768
        },
        {
          "id": "glm-5",
          "name": "GLM-5",
          "reasoning": false,
          "input": ["text"],
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
          "contextWindow": 202752,
          "maxTokens": 16384
        }
      ]
    }
  }
}

In openclaw.json, modify agents.defaults to add the model list information (the primary field is set to glm-5 by default, but you can change it to any model supported in models):

"agents": {
  "defaults": {
    "model": {
      "primary": "tencent-coding-plan/glm-5"
    },
    "models": {
      "tencent-coding-plan/tc-code-latest": {},
      "tencent-coding-plan/hunyuan-2.0-instruct": {},
      "tencent-coding-plan/hunyuan-2.0-thinking": {},
      "tencent-coding-plan/hunyuan-t1": {},
      "tencent-coding-plan/hunyuan-turbos": {},
      "tencent-coding-plan/minimax-m2.5": {},
      "tencent-coding-plan/kimi-k2.5": {},
      "tencent-coding-plan/glm-5": {}
    }
  }
}

Restart the service: To apply the configuration, run the following command in the terminal to restart OpenClaw.
```
openclaw gateway restart
```

DeepSeek V4

Connect to the terminal without a password: Log in to the Simple Application Server console. Find your server's card, click Remote Connection, and in the Connect with One-click on Workbench area, click Log on Now.
Go to the DeepSeek Open Platform to get an API key.

Modify the configuration file: Run the following command in the terminal to open the configuration file.

vim ~/.openclaw/openclaw.json

In models.providers, add the following configuration and save your changes (replace <YOUR_API_KEY> with the API key from the previous step):

"models": {
  "mode": "merge",
  "providers": {
    "deepseek": {
      "baseUrl": "https://api.deepseek.com/v1",
      "apiKey": "YOUR_API_KEY",
      "api": "openai-completions",
      "models": [
        {"id": "deepseek-v4-flash", "name": "DeepSeek V4 Flash"},
        {"id": "deepseek-v4-pro", "name": "DeepSeek V4 Pro"}
      ]
    }
  }
}

Modify agents.defaults in openclaw.json to add the model list information, and then save and exit (the primary field is set to deepseek-v4-flash by default and can be changed to any model supported in the models list):

"agents": {
  "defaults": {
    "model": {
      "primary": "deepseek/deepseek-v4-flash"
    },
    "models": {
      "deepseek/deepseek-v4-flash": {},
      "deepseek/deepseek-v4-pro": {}
    }
  }
}

Restart the service to apply the configuration: After saving the file, run the following command in the terminal to restart OpenClaw.
```
openclaw gateway restart
```

Volcengine agent plan

Password-free login to the terminal: Log in to the Simple Application Server console, find the card for your target server, and click Remote Connection. In the Connect with One-click on Workbench area, click Log on Now.
Ensure your account is subscribed to the Ark Agent Plan, and get your API key from the Volcengine console.

Modify the configuration file: To edit the configuration file, run the following command in the terminal.

vim ~/.openclaw/openclaw.json

Add the following to the models.providers section, replacing <ARK_API_KEY> with your API key.

Warning

Do not use https://ark.cn-beijing.volces.com/api/v3 as the base URL. This endpoint does not consume your Agent Plan quota and will result in extra charges.

"models": {
  "mode": "merge",
  "providers": {
    "volcengine-agent-plan": {
      "baseUrl": "https://ark.cn-beijing.volces.com/api/plan/v3",
      "apiKey": "ARK_API_KEY",
      "api": "openai-completions",
      "models": [
        {
          "id": "ark-code-latest",
          "name": "ark-code-latest",
          "contextWindow": 256000,
          "maxTokens": 32000,
          "input": ["text", "image"]
        },
        {
          "id": "doubao-seed-2.0-code",
          "name": "doubao-seed-2.0-code",
          "contextWindow": 256000,
          "maxTokens": 128000,
          "input": ["text", "image"]
        },
        {
          "id": "doubao-seed-2.0-pro",
          "name": "doubao-seed-2.0-pro",
          "contextWindow": 256000,
          "maxTokens": 128000,
          "input": ["text", "image"]
        },
        {
          "id": "doubao-seed-2.0-lite",
          "name": "doubao-seed-2.0-lite",
          "contextWindow": 256000,
          "maxTokens": 128000,
          "input": ["text", "image"]
        },
        {
          "id": "doubao-seed-2.0-mini",
          "name": "doubao-seed-2.0-mini",
          "contextWindow": 256000,
          "maxTokens": 128000,
          "input": ["text", "image"]
        },
        {
          "id": "glm-5.1",
          "name": "glm-5.1",
          "contextWindow": 200000,
          "maxTokens": 128000,
          "input": ["text"]
        },
        {
          "id": "deepseek-v3.2",
          "name": "deepseek-v3.2",
          "contextWindow": 128000,
          "maxTokens": 32000,
          "input": ["text"]
        },
        {
          "id": "minimax-2.7",
          "name": "minimax-2.7",
          "contextWindow": 200000,
          "maxTokens": 128000,
          "input": ["text"]
        },
        {
          "id": "kimi-k2.6",
          "name": "kimi-k2.6",
          "contextWindow": 256000,
          "maxTokens": 32000,
          "input": ["text", "image"]
        }
      ]
    }
  }
}

In openclaw.json, update the agents.defaults section with the models you want to enable. The primary field specifies the default model. In this example, the primary model is set to glm-5.1, but you can change it to any other model supported in the models object.

"agents": {
  "defaults": {
    "model": {
      "primary": "volcengine-agent-plan/glm-5.1"
    },
    "models": {
      "volcengine-agent-plan/ark-code-latest": {},
      "volcengine-agent-plan/doubao-seed-2.0-code": {},
      "volcengine-agent-plan/doubao-seed-2.0-pro": {},
      "volcengine-agent-plan/doubao-seed-2.0-lite": {},
      "volcengine-agent-plan/doubao-seed-2.0-mini": {},
      "volcengine-agent-plan/glm-5.1": {},
      "volcengine-agent-plan/deepseek-v3.2": {},
      "volcengine-agent-plan/minimax-2.7": {},
      "volcengine-agent-plan/kimi-k2.6": {}
    }
  }
}

Restart the service to apply the configuration: Save the file and run the following command in the terminal to restart OpenClaw.
```
openclaw gateway restart
```

FAQ

Switch default model to qwen3.6-plus

The Team Edition of Token Plan defaults to the qwen3.6-plus primary model. If your current default is a different model, follow these steps to switch back:

In the OpenClaw WebUI, select Configuration > RAW from the left menu bar.

Ensure that models.providers.bailian-token-plan.models includes the qwen3.6-plus model configuration. If not, add the following:

{
  "id": "qwen3.6-plus",
  "name": "qwen3.6-plus",
  "reasoning": false,
  "input": ["text", "image"],
  "contextWindow": 1000000,
  "maxTokens": 65536,
  "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
  "compat": { "thinkingFormat": "qwen" }
}

Set the agents.defaults.model.primary parameter to bailian-token-plan/qwen3.6-plus.
Click Save, then Update to apply the configuration.