OpenClaw

Merge the following into existing OpenClaw configuration and securely set NEKOCLOUD_API_KEY in its process environment. This example uses Chat Completions only.

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "nekocloud/REPLACE_WITH_MODEL_ID"
      }
    }
  },
  "models": {
    "mode": "merge",
    "providers": {
      "nekocloud": {
        "baseUrl": "https://api.nekocloud.vip/v1",
        "apiKey": "${NEKOCLOUD_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "REPLACE_WITH_MODEL_ID",
            "name": "NekoCloud"
          }
        ]
      }
    }
  }
}

Model references use provider/model; the API model ID does not include nekocloud/. Register the provider model list as well as the default model. For Responses, select openai-responses when supported by your version. For Anthropic use anthropic-messages with the documented base URL handling. Reload by the supported configuration flow and check openclaw models list. Do not change Gateway network exposure or disable approvals to connect a provider.

Verification and safety

Back up existing settings and merge only relevant fields; preserve other providers, plugins, MCP and permissions. Protect keys and backups, never commit them. Variables must reach the actual agent process; Remote SSH, containers and desktop processes have separate environments.

Relaunch, select the NekoCloud model, send a short message and match time, model and charge in Usage. Then read a non-sensitive file in an isolated project and verify the tool call, returned result and final answer. Tests can incur charges. Keep approval controls enabled.

This is adapted from official provider configuration guidance, not proof that every model or the complete NekoCloud tool chain has been tested. Check Model Plaza, key groups and troubleshooting.

Official reference

https://docs.openclaw.ai/concepts/model-providers/custom-providers