OpenClaw

OpenClaw connects messaging channels, models and tools. This guide uses a separate bamboo provider so existing OpenAI profiles can be preserved.

API key

Create an inference key in API Keys, then set it in the process that runs OpenClaw:

export BAMBOO_API_KEY="sk-your-api-key"

Provider configuration

Merge this configuration into the existing file. Replace your-model-id with an exact ID from Models; do not overwrite unrelated messaging, tool or permission settings.

{
  "models": {
    "providers": {
      "bamboo": {
        "baseUrl": "https://api.bamboonode.cn/v1",
        "apiKey": "${BAMBOO_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "your-model-id",
            "name": "Bamboo Model"
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "bamboo/your-model-id"
      }
    }
  }
}

Verify

1. Restart OpenClaw to reload its environment and configuration.
2. Confirm the selected model is bamboo/your-model-id.
3. Send a short message through a connected channel.
4. If the primary model fails, temporarily turn off fallback to confirm whether Bamboo received the request.

The service process must inherit BAMBOO_API_KEY; exporting it in an unrelated terminal is insufficient. Image inputs and tool calls depend on the model. Test plain text first.

References

• Chat Completions
• OpenClaw documentation
• Project repository