Tencent Cloud / OpenClaw Custom Model Configuration

OpenClaw Custom Model Configuration screen; field positions are for refe…

OpenAI Compatible Configuration

Suitable for models compatible with Chat Completions, such as GPT, DeepSeek, Qwen, GLM, Kimi, and MiniMax:

{
  models: {
    mode: "merge",
    providers: {
      guishu: {
        baseUrl: "https://api.llm-token.cn/v1",
        apiKey: "YOUR_API_KEY",
        api: "openai-completions",
        models: [
          {
            id: "deepseek-v4-flash",
            name: "deepseek-v4-flash",
            input: ["text"]
          }
        ]
      }
    }
  }
}

Anthropic Messages Configuration

When the client explicitly requires the Anthropic Messages protocol, only change the api and the model ID:

{
  models: {
    mode: "merge",
    providers: {
      guishu: {
        baseUrl: "https://api.llm-token.cn/v1",
        apiKey: "YOUR_API_KEY",
        api: "anthropic-messages",
        models: [
          {
            id: "claude-sonnet-4-6",
            name: "claude-sonnet-4-6",
            input: ["text", "image"]
          }
        ]
      }
    }
  }
}

Checks Before Saving

• The OpenClaw field names are baseUrl and apiKey, not base_url or api_key.
• In api, enter the adapter name: openai-completions or anthropic-messages, not the /messages path.
• Uniformly enter https://api.llm-token.cn/v1 for the Base URL, and stop appending /chat/completions.
• The model ID is updated from time to time; copy it from the model list rather than copying old screenshots.
• After saving, run openclaw models list, then switch using the openclaw models set guishu/ model ID.