Documentation Index
Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
Use this file to discover all available pages before exploring further.
使用 CometAPI 作为 OpenClaw 的模型提供方——一个 API 接入 500+ 模型。
先决条件
- Node.js ≥ 22 —— 推荐通过 nvm 安装
- 一个拥有有效 API key 的 CometAPI 账户 —— 点此获取
安装或更新 OpenClaw
推荐 —— 使用官方安装脚本：curl -fsSL https://openclaw.ai/install.sh | bash
npm install -g openclaw@latest
openclaw onboard --install-daemon
openclaw gateway status
openclaw dashboard
存储你的 CometAPI key
将你的 key 写入 ~/.openclaw/.env，这样 daemon 就可以读取，而无需将其硬编码到配置文件中：printf 'COMETAPI_KEY=%s\n' 'your-<COMETAPI_KEY>-key' >> ~/.openclaw/.env
chmod 600 ~/.openclaw/.env
如果你已经通过 shell、service manager 或密钥管理工作流注入了 COMETAPI_KEY，请跳过此步骤——下方配置无论变量以何种方式设置，都使用 $\{COMETAPI_KEY\}。
配置 CometAPI providers
CometAPI 支持 四种 API 格式。将一个或多个 provider 配置块添加到 ~/.openclaw/openclaw.json：| Provider | API 格式 | 调用的端点 | Base URL |
|---|
cometapi-openai | openai-completions | POST /v1/chat/completions | https://api.cometapi.com/v1 |
cometapi-openai-responses | openai-responses | POST /v1/responses | https://api.cometapi.com/v1 |
cometapi-claude | anthropic-messages | POST /messages | https://api.cometapi.com |
cometapi-google | google-generative-ai | POST /v1beta/... | https://api.cometapi.com/v1beta |
{
"agents": {
"defaults": {
"model": {
"primary": "cometapi-claude/your-claude-model-id"
}
}
},
"models": {
"mode": "merge",
"providers": {
"cometapi-openai": {
"baseUrl": "https://api.cometapi.com/v1",
"apiKey": "${COMETAPI_KEY}",
"api": "openai-completions",
"models": [{ "id": "your-chat-model-id", "name": "OpenAI-compatible text model" }]
},
"cometapi-openai-responses": {
"baseUrl": "https://api.cometapi.com/v1",
"apiKey": "${COMETAPI_KEY}",
"api": "openai-responses",
"models": [{ "id": "your-responses-model-id", "name": "Responses API model" }]
},
"cometapi-claude": {
"baseUrl": "https://api.cometapi.com",
"apiKey": "${COMETAPI_KEY}",
"api": "anthropic-messages",
"models": [{ "id": "your-claude-model-id", "name": "Claude family model" }]
},
"cometapi-google": {
"baseUrl": "https://api.cometapi.com/v1beta",
"apiKey": "${COMETAPI_KEY}",
"api": "google-generative-ai",
"models": [{ "id": "your-gemini-model-id", "name": "Gemini family model" }]
}
}
}
}
provider/model 引用在不同格式之间切换路由。将每个 your-...-model-id 占位符替换为与对应 provider 配置块匹配的、来自 CometAPI 模型页面 的当前 model ID。对于需要 OpenAI Responses API 的模型，请使用 cometapi-openai-responses（api: "openai-responses"）。对于使用经典聊天补全路径的模型，请使用 cometapi-openai（api: "openai-completions"）。两者共享相同的 baseUrl（https://api.cometapi.com/v1）；唯一的区别是 OpenClaw 调用的是哪个下游端点。
此设置 不需要 auth-profiles.json 文件。provider key 通过 models.providers.*.apiKey 并借助 $\{COMETAPI_KEY\} 环境变量解析。只有当你希望在多个 key 之间按 profile 轮换凭证时，才需要 auth-profiles.json。
重启并验证
添加 .env 或修改 provider 配置后，重启 gateway：然后运行诊断：openclaw models status
openclaw models list --provider cometapi-claude
openclaw doctor
openclaw models status 会将主模型解析为 cometapi-claude/your-claude-model-id，且 CometAPI providers 不会出现缺失认证警告openclaw models list --provider cometapi-claude 会列出你配置的模型openclaw doctor 会报告 CometAPI providers 不存在配置或认证错误
切换模型
切换模型
# Set the default model in config
openclaw models set cometapi-claude/your-claude-model-id
# Switch for the current chat session
/model cometapi-openai/your-chat-model-id
/model cometapi-openai-responses/your-responses-model-id
/model cometapi-claude/your-claude-model-id
/model cometapi-google/your-gemini-model-id
故障排查
