openclaw使用免费模型顶级模型（nvidia免费模型使用）

英伟达模型地址
https://build.nvidia.com/models

配置步骤

1. 注册账号登录，申请一个Api key。

2. 找到openclaw配置文件文件夹，一般在用户目录下：

   C:\\Users\\具体用户\\.openclaw
   

3. 找到openclaw.json文件。
   

{
  "models": {
    "providers": {
      "qwen-portal": {
        "baseUrl": "https://portal.qwen.ai/v1",
        "apiKey": "qwen-oauth",
        "api": "openai-completions",
        "models": [
          {
            "id": "coder-model",
            "name": "Qwen Coder",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          },
          {
            "id": "vision-model",
            "name": "Qwen Vision",
            "reasoning": false,
            "input": [
              "text",
              "image"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          }
        ]
      },
      "nvidia": {
        "baseUrl": "https://integrate.api.nvidia.com/v1",
        "apiKey": "XXXXXXX",
        "api": "openai-completions",
        "models": [
          {
            "id": "z-ai/glm5",
            "name": "z-ai/glm5",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          }
        ]
      }
    }
  }
}

“apiKey”: “XXXXXXX”, 需要修改成自己的。

4. 点击英伟达的模型，右上角有个查看调用地址。增加英伟达的模型，我增加的是glm5：
   

5. 主要要加前面的nvidia/
   

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "nvidia/z-ai/glm5"
      },
      "models": {
        "qwen-portal/coder-model": {
          "alias": "qwen"
        },
        "nvidia/z-ai/glm5": {},
        "qwen-portal/vision-model": {}
      },
      "workspace": "C:\\Users\\Guocan\\.openclaw\\workspace",
      "compaction": {
        "mode": "safeguard"
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }
}

6. 以上修改好后，关闭已开启的网关服务，重启网关服务。

7. 进行测试，已经使用新模型。

openclaw学习成长系列：点击下方继续学习

openClaw安装Windows版

openclaw使用免费模型顶级模型（英伟达免费模型使用
openclaw实现接入QQ机器人