Appearance
OpenClaw
OpenClaw 是一个开源的个人 AI 助手平台,支持通过终端、Web UI 等多种方式与 AI 交互。通过配置 OpenAI 兼容端点,可接入 LimAPI 使用平台上的全部模型。
安装 OpenClaw
OpenClaw 需要 Node.js 22.19.0 或更高版本(仅 npm 安装方式需要)。可通过以下命令检查 Node.js 版本:
bash
node --version如果未安装或版本过低,请访问 Node.js 官网下载安装。
macOS / Linux
推荐使用官方安装脚本:
bash
curl -fsSL https://raw.githubusercontent.com/openclaw/openclaw/main/install.sh | bash或通过 npm 全局安装:
bash
npm install -g openclaw@latestWindows
在 PowerShell 或 CMD 中通过 npm 全局安装:
bash
npm install -g openclaw@latest其他安装方式请前往 OpenClaw 官方仓库查看。
首次安装后,OpenClaw 会自动启动配置向导完成初始设置,也可以手动执行 openclaw onboard 进行配置。向导中各配置项建议如下:
| 配置项 | 建议配置 |
|---|---|
| I understand this is powerful and inherently risky. Continue? | 选择 Yes |
| Onboarding mode | 选择 QuickStart |
| Model/auth provider | 选择 Skip for now(稍后配置 LimAPI 模型) |
| Filter models by provider | 选择 All providers |
| Default model | 选择 Keep current |
| Select channel (QuickStart) | 选择 Skip for now(稍后配置渠道) |
| Configure skills now? (recommended) | 选择 No |
| How do you want to hatch your bot? | 选择 Do this later |
配置接入凭证
| 配置项 | 说明 |
|---|---|
| API Key | Portal 创建的 LimAPI API Key(sk- 开头) |
| Base URL | https://limapi.com/api/anthropic(Anthropic 兼容端点) |
| 可用模型 | 平台支持的任意模型,完整列表通过 GET /api/v1/models 查询或在 Portal 模型广场查看 |
配置文件位于 ~/.openclaw/openclaw.json,OpenClaw 启动时会自动读取。
说明:示例配置禁用了网关鉴权(
auth.mode: none),仅适合单机本地使用。如需共享或远程访问,请运行openclaw doctor --fix启用 token 鉴权。
首次配置:复制以下内容到配置文件,将 YOUR_API_KEY 替换为 LimAPI API Key。示例预置了平台 16 个常用模型,可按需增删(完整列表见 GET /api/v1/models)。
已有配置:若需保留已有配置,请勿直接全量替换,只需将 models.providers.limapi 节点合并进 models.providers,并追加 agents.defaults 中的 limapi/ 模型条目。
json
{
"meta": {
"lastTouchedVersion": "2026.2.1",
"lastTouchedAt": "2026-08-10T00:00:00.000Z"
},
"models": {
"mode": "merge",
"providers": {
"limapi": {
"baseUrl": "https://limapi.com/api/anthropic",
"apiKey": "YOUR_API_KEY",
"api": "anthropic-messages",
"models": [
{
"id": "qwen3.8-max",
"name": "qwen3.8-max",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3.7-max",
"name": "qwen3.7-max",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3.7-plus",
"name": "qwen3.7-plus",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3.6-plus",
"name": "qwen3.6-plus",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "qwen3.6-flash",
"name": "qwen3.6-flash",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "claude-opus-5",
"name": "claude-opus-5",
"reasoning": false,
"input": ["text"],
"contextWindow": 1000000,
"maxTokens": 32768,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "claude-sonnet-4-6",
"name": "claude-sonnet-4-6",
"reasoning": false,
"input": ["text"],
"contextWindow": 200000,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"reasoning": true,
"input": ["text"],
"contextWindow": 131072,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "kimi-k2.7-code",
"name": "kimi-k2.7-code",
"reasoning": true,
"input": ["text"],
"contextWindow": 262144,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "kimi-k2.6",
"name": "kimi-k2.6",
"reasoning": false,
"input": ["text"],
"contextWindow": 131072,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5.2",
"name": "glm-5.2",
"reasoning": true,
"input": ["text"],
"contextWindow": 1048576,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5.1",
"name": "glm-5.1",
"reasoning": true,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "glm-5",
"name": "glm-5",
"reasoning": true,
"input": ["text"],
"contextWindow": 202752,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"reasoning": true,
"input": ["text"],
"contextWindow": 196608,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "limapi/qwen3.8-max"
},
"models": {
"limapi/qwen3.8-max": {},
"limapi/qwen3.7-max": {},
"limapi/qwen3.7-plus": {},
"limapi/qwen3.6-plus": {},
"limapi/qwen3.6-flash": {},
"limapi/claude-opus-5": {},
"limapi/claude-sonnet-4-6": {},
"limapi/deepseek-v4-pro": {},
"limapi/deepseek-v4-flash": {},
"limapi/deepseek-v3.2": {},
"limapi/kimi-k2.7-code": {},
"limapi/kimi-k2.6": {},
"limapi/glm-5.2": {},
"limapi/glm-5.1": {},
"limapi/glm-5": {},
"limapi/MiniMax-M2.5": {}
}
}
},
"gateway": {
"mode": "local",
"auth": { "mode": "none" }
}
}| 字段 | 说明 |
|---|---|
models.providers.limapi.baseUrl | LimAPI Anthropic 兼容端点,固定为 https://limapi.com/api/anthropic |
models.providers.limapi.apiKey | Portal 创建的 API Key |
models.providers.limapi.api | 协议类型,固定为 anthropic-messages |
models.providers.limapi.models | 向 OpenClaw 声明的模型清单,含上下文窗口、最大输出等元信息 |
agents.defaults.model.primary | 默认使用的模型,格式为 limapi/<模型名称> |
写入后重启网关使配置生效:
bash
openclaw gateway restart验证
启动 OpenClaw 进入交互界面:
bash
openclaw在交互界面中发送一条消息(如「你好」),模型正常返回响应即配置成功。也可输入 /status 查看当前模型与连接状态。如需切换模型,输入 /model <模型名称>。
常见命令
| 命令 | 说明 | 示例 |
|---|---|---|
/help | 显示可用命令的快速摘要 | /help |
/status | 查看当前模型、会话、网关等状态信息 | /status |
/model <模型名称> | 切换当前会话使用的模型 | /model qwen3.8-max |
/new | 开始一个新会话 | /new |
/compact | 压缩对话历史,释放上下文窗口空间 | /compact |
/skills | 展示全部可用的 Skill | /skills |
常见问题
报错 "HTTP 401: Incorrect API key provided."
可能原因:
- API Key 无效、过期、为空或格式错误。请在 Portal 的「API Keys」页面确认 Key 状态,并确保复制完整且无空格。
- API Key 与 Base URL 不匹配。LimAPI 的 Anthropic 兼容端点固定为
https://limapi.com/api/anthropic,请勿使用其他平台地址。 - 历史配置缓存导致配置错误。可检查
~/.openclaw/openclaw.json中models.providers.limapi节点后重新写入。
配置后仍连接 OpenClaw 官方服务
修改配置文件后需重启网关使配置生效:
bash
openclaw gateway restart如何查看已配置的模型?
在终端输入 openclaw 进入交互界面,接着输入 /model 查看模型列表。按回车键选中模型,按 Esc 键退出模型列表。
一键配置
使用 LimAPI Agent 桌面客户端 可自动合并写入 ~/.openclaw/openclaw.json。