OpenClaw

OpenClaw 是什么

OpenClaw 是开源、自托管的个人 AI 助手和 Gateway，可以把 WhatsApp、Slack、Discord、Telegram、iMessage 和 WebChat 等聊天渠道连接到 AI 代理。配置自定义 OpenAI 兼容和 Anthropic 兼容模型提供商后，它可以通过 Capriole AI 发送受支持的模型请求。

前置条件

开始前请确保你已经拥有以下内容。

Capriole AI 账户，可在此处注册
Capriole AI API Key，可在此处获取

安装

curl -fsSL https://openclaw.ai/install.sh | bash -s -- --no-onboard

配置

模型验证

OpenClaw 2026.4.21：openai/gpt-6.1-sol、openai/gpt-6-sol、openai/gpt-6-luna、anthropic/claude-fable-5-1、anthropic/claude-opus-5-5、google/gemini-3.8-flash 和 zai/glm-5.3-flash 已通过本地文件读取工具和最终答案检查。 claude-latest 解析到 Fable 5.1。原有具体模型 ID 继续可用。下方容量配置参考 GPT-6 Astra、GPT-6.1 Sol、GPT-6 Sol、GPT-6 Luna、Fable 5.1、Opus 5.5、Gemini 3.8 Flash 和 GLM 5.3 Flash 的官方规格。这些是客户端的模型容量设置，不是每次请求的输出目标，也不是已验证的 VectorEngine 上限。本地任务检查使用 contextWindow=200000 和 maxTokens=2048，尚未验证满容量请求。Fable 5.1 也通过了 Anthropic Messages 路径检查。 xai/grok-4.6 能接受 Chat Completions 请求，但未通过编码 Agent 任务检查，因此不加入下方配置。直接调用上游的检查也发现 Grok 4.5 的工具使用不稳定；API 请求完成不代表 Agent 答案正确。配置 GPT 提供商。

export CUSTOM_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
export CAPRIOLE_OPENAI_BASE_URL="https://api.caprioletech.com/v1"

openclaw onboard --non-interactive \
  --accept-risk \
  --mode local \
  --auth-choice custom-api-key \
  --custom-base-url "$CAPRIOLE_OPENAI_BASE_URL" \
  --custom-model-id "openai-latest" \
  --custom-provider-id "capriole-ai-openai" \
  --custom-compatibility openai \
  --secret-input-mode ref \
  --gateway-port 18789 \
  --gateway-bind loopback \
  --skip-channels \
  --skip-search \
  --skip-skills \
  --skip-health \
  --no-install-daemon

openclaw config set models.providers.capriole-ai-openai.request.auth \
  '{"mode":"authorization-bearer","token":"${CUSTOM_API_KEY}"}' \
  --strict-json

openclaw config set models.providers.capriole-ai-openai.api \
  '"openai-responses"' \
  --strict-json

openclaw config set models.providers.capriole-ai-openai.models \
  '[
    {
      "id": "openai-latest",
      "name": "OpenAI latest",
      "api": "openai-responses",
      "contextWindow": 400000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-6-astra",
      "name": "GPT-6 Astra",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-6-sol",
      "name": "GPT-6 Sol",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-6-luna",
      "name": "GPT-6 Luna",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-5.6-terra",
      "name": "GPT 5.6 Thinking",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-5.6-luna",
      "name": "GPT 5.6",
      "api": "openai-responses",
      "contextWindow": 1050000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "openai/gpt-5.5",
      "name": "GPT 5.5",
      "api": "openai-responses",
      "contextWindow": 400000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    }
  ]' \
  --strict-json

配置 Claude、Grok、GLM 和 Kimi Chat Completions 提供商。

export CUSTOM_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"

openclaw config set models.providers.capriole-ai-compatible \
  '{
    "baseUrl": "https://api.caprioletech.com/v1",
    "apiKey": "${CUSTOM_API_KEY}",
    "api": "openai-completions",
    "models": [
      {
        "id": "anthropic/claude-fable-5-1",
        "name": "Fable 5.1",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "anthropic/claude-fable-5",
        "name": "Fable 5",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "anthropic/claude-opus-5-5",
        "name": "Opus 5.5",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "anthropic/claude-opus-5",
        "name": "Opus 5",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "google/gemini-3.8-flash",
        "name": "Gemini 3.8 Flash",
        "api": "openai-completions",
        "contextWindow": 1048576,
        "maxTokens": 65536,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "xai/grok-4.7",
        "name": "Grok 4.7",
        "api": "openai-completions",
        "contextWindow": 500000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "xai/grok-4.5",
        "name": "Grok 4.5",
        "api": "openai-completions",
        "contextWindow": 500000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "zai/glm-5.3-flash",
        "name": "GLM 5.3 Flash",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "zai/glm-5.2",
        "name": "GLM 5.2",
        "api": "openai-completions",
        "contextWindow": 1000000,
        "maxTokens": 128000,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      },
      {
        "id": "moonshot/kimi-k3",
        "name": "Kimi K3",
        "api": "openai-completions",
        "contextWindow": 1048576,
        "maxTokens": 131072,
        "input": ["text"],
        "reasoning": true,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      }
    ]
  }' \
  --strict-json

配置 Anthropic 提供商。

export CUSTOM_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
export CAPRIOLE_ANTHROPIC_BASE_URL="https://api.caprioletech.com"

openclaw onboard --non-interactive \
  --accept-risk \
  --mode local \
  --auth-choice custom-api-key \
  --custom-base-url "$CAPRIOLE_ANTHROPIC_BASE_URL" \
  --custom-model-id "claude-latest" \
  --custom-provider-id "capriole-ai-anthropic" \
  --custom-compatibility anthropic \
  --secret-input-mode ref \
  --gateway-port 18789 \
  --gateway-bind loopback \
  --skip-channels \
  --skip-search \
  --skip-skills \
  --skip-health \
  --no-install-daemon

openclaw config set models.providers.capriole-ai-anthropic.request.auth \
  '{"mode":"authorization-bearer","token":"${CUSTOM_API_KEY}"}' \
  --strict-json

openclaw config set models.providers.capriole-ai-anthropic.api \
  '"anthropic-messages"' \
  --strict-json

openclaw config set models.providers.capriole-ai-anthropic.models \
  '[
    {
      "id": "claude-latest",
      "name": "Claude latest",
      "api": "anthropic-messages",
      "contextWindow": 1000000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-fable-5-1",
      "name": "Fable 5.1",
      "api": "anthropic-messages",
      "contextWindow": 1000000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-fable-5",
      "name": "Fable 5",
      "api": "anthropic-messages",
      "contextWindow": 1000000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-opus-5-5",
      "name": "Opus 5.5",
      "api": "anthropic-messages",
      "contextWindow": 1000000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-opus-5",
      "name": "Opus 5",
      "api": "anthropic-messages",
      "contextWindow": 1000000,
      "maxTokens": 128000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-opus-4-8",
      "name": "Opus 4.8",
      "api": "anthropic-messages",
      "contextWindow": 200000,
      "maxTokens": 32000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-opus-4-7",
      "name": "Opus 4.7",
      "api": "anthropic-messages",
      "contextWindow": 200000,
      "maxTokens": 32000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-opus-4-6",
      "name": "Opus 4.6",
      "api": "anthropic-messages",
      "contextWindow": 200000,
      "maxTokens": 32000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    },
    {
      "id": "claude-sonnet-4-6",
      "name": "Sonnet 4.6",
      "api": "anthropic-messages",
      "contextWindow": 200000,
      "maxTokens": 32000,
      "input": ["text"],
      "reasoning": true,
      "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
    }
  ]' \
  --strict-json

允许默认代理使用已经配置的 Capriole AI 模型。

openclaw config set agents.defaults.models \
  '{"capriole-ai-openai/openai-latest":{},"capriole-ai-openai/openai/gpt-6-astra":{},"capriole-ai-openai/openai/gpt-6.1-sol":{},"capriole-ai-openai/openai/gpt-6-sol":{},"capriole-ai-openai/openai/gpt-6-luna":{},"capriole-ai-openai/openai/gpt-5.6-terra":{},"capriole-ai-openai/openai/gpt-5.6-luna":{},"capriole-ai-openai/openai/gpt-5.5":{},"capriole-ai-compatible/anthropic/claude-fable-5-1":{},"capriole-ai-compatible/anthropic/claude-fable-5":{},"capriole-ai-compatible/anthropic/claude-opus-5-5":{},"capriole-ai-compatible/anthropic/claude-opus-5":{},"capriole-ai-compatible/google/gemini-3.8-flash":{},"capriole-ai-compatible/xai/grok-4.7":{},"capriole-ai-compatible/xai/grok-4.5":{},"capriole-ai-compatible/zai/glm-5.3-flash":{},"capriole-ai-compatible/zai/glm-5.2":{},"capriole-ai-compatible/moonshot/kimi-k3":{},"capriole-ai-anthropic/claude-latest":{},"capriole-ai-anthropic/claude-fable-5-1":{},"capriole-ai-anthropic/claude-fable-5":{},"capriole-ai-anthropic/claude-opus-5-5":{},"capriole-ai-anthropic/claude-opus-5":{},"capriole-ai-anthropic/claude-opus-4-8":{},"capriole-ai-anthropic/claude-opus-4-7":{},"capriole-ai-anthropic/claude-opus-4-6":{},"capriole-ai-anthropic/claude-sonnet-4-6":{}}' \
  --strict-json

运行 OpenClaw

启动 Gateway。

export CUSTOM_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
openclaw gateway --force --port 18789

在另一个终端中打开 TUI。

export CUSTOM_API_KEY="YOUR_CAPRIOLE_AI_API_KEY"
openclaw tui

支持的模型

OpenClaw 可以通过 Capriole AI 使用 OpenAI latest、GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna, GPT 5.6 Thinking、GPT 5.6、GPT 5.5、Fable 5.1、Fable 5、Opus 5.5、Opus 5、Grok 4.7、Grok 4.5、Gemini 3.8 Flash、GLM 5.3 Flash、GLM 5.2、Kimi K3、Claude latest、Opus 4.8、Opus 4.7、Opus 4.6 和 Sonnet 4.6。Fable 5 和 Opus 5 可以使用 Chat Completions 兼容提供商，也可以使用 Anthropic Messages 提供商。

openai-latest
openai/gpt-6-astra
openai/gpt-6.1-sol
openai/gpt-6-sol
openai/gpt-6-luna
openai/gpt-5.6-terra
openai/gpt-5.6-luna
openai/gpt-5.5
anthropic/claude-fable-5-1
anthropic/claude-fable-5
anthropic/claude-opus-5-5
anthropic/claude-opus-5
google/gemini-3.8-flash
xai/grok-4.7
xai/grok-4.5
zai/glm-5.3-flash
zai/glm-5.2
moonshot/kimi-k3
claude-latest
claude-fable-5-1
claude-fable-5
claude-opus-5-5
claude-opus-5
claude-opus-4-8
claude-opus-4-7
claude-opus-4-6
claude-sonnet-4-6

故障排除

为什么 GPT 请求失败

确认 models.providers.capriole-ai-openai.api 已设为 "openai-responses"，并且 baseUrl 是 https://api.caprioletech.com/v1。

为什么 Grok、GLM 或 Kimi 请求失败

确认 models.providers.capriole-ai-compatible.api 已设为 "openai-completions"，并且 baseUrl 是 https://api.caprioletech.com/v1。

为什么 Anthropic 请求失败

确认 models.providers.capriole-ai-anthropic.api 已设为 "anthropic-messages"，并且 Anthropic baseUrl 是不含 /v1 的 https://api.caprioletech.com。

为什么身份验证失败

在启动 openclaw gateway 的终端和启动 openclaw tui 的终端中分别导出 CUSTOM_API_KEY。

为什么 OpenClaw 提示模型不被允许或不可用

运行 openclaw models list，然后确认所选模型和 agents.defaults.models Allowlist 都包含对应的 Capriole AI 模型引用，例如 capriole-ai-openai/openai-latest、capriole-ai-compatible/xai/grok-4.5、capriole-ai-compatible/moonshot/kimi-k3 或 capriole-ai-anthropic/claude-latest。如果 Capriole AI 模型显示为缺失，请使用上方所示的完整对象更新模型条目。当前 OpenClaw 版本配置自定义提供商模型时，只提供 id 和 name 还不够。

为什么 Gateway 无法启动

运行 openclaw status、openclaw gateway status、openclaw logs --follow 和 openclaw doctor。先修复 Schema、gateway.mode 或服务问题，再重新尝试。

为什么端口 `18789` 无法使用

选择另一个本地端口，并在 Gateway 和客户端配置中使用相同端口。对于服务模式安装，更改端口后运行 openclaw doctor --fix 或 openclaw gateway install --force。

说明

OpenClaw 自定义提供商要求提供商 API 模式与 Capriole AI 端点系列匹配。
OpenClaw 2026.4.21 可以通过 openai-completions，使用 Grok 4.5、GLM 5.2 和 Kimi K3 完成本地 exec 工具工作流。
Capriole AI 处理模型请求。OpenClaw 仍可通过自身的 Gateway、渠道和代理设置决定助手的最终行为。
官方参考资料包括 OpenClaw 安装、OpenClaw 自定义提供商、OpenClaw 模型提供商和 OpenClaw 故障排除。

开始使用

端点

编程代理集成

OpenClaw 是什么

前置条件

安装

配置

模型验证

运行 OpenClaw

支持的模型

故障排除

为什么 GPT 请求失败

为什么 Grok、GLM 或 Kimi 请求失败

为什么 Anthropic 请求失败

为什么身份验证失败

为什么 OpenClaw 提示模型不被允许或不可用

为什么 Gateway 无法启动

为什么端口 `18789` 无法使用

说明

​OpenClaw 是什么

​前置条件

​安装

​配置

​模型验证

​运行 OpenClaw

​支持的模型

​故障排除

​为什么 GPT 请求失败

​为什么 Grok、GLM 或 Kimi 请求失败

​为什么 Anthropic 请求失败

​为什么身份验证失败

​为什么 OpenClaw 提示模型不被允许或不可用

​为什么 Gateway 无法启动

​为什么端口 18789 无法使用

​说明

OpenClaw 是什么

前置条件

安装

配置

模型验证

运行 OpenClaw

支持的模型

故障排除

为什么 GPT 请求失败

为什么 Grok、GLM 或 Kimi 请求失败

为什么 Anthropic 请求失败

为什么身份验证失败

为什么 OpenClaw 提示模型不被允许或不可用

为什么 Gateway 无法启动

为什么端口 `18789` 无法使用

说明