Skip to main content
OpenClaw is an open-source personal AI assistant that can run on your own devices and connect to messaging channels you already use. OpenClaw can use NagaAI through our Chat Completions endpoint.

​
Prerequisites

​
Configuration

1

Get a NagaAI API key

Create an API key in the dashboard: https://naga.ac/dashboard.
If you’re new to NagaAI, follow the Quickstart first.
2

Update your OpenClaw config

Open ~/.openclaw/openclaw.json and add a provider named nagaai:
{
  "models": {
    "mode": "merge",
    "providers": {
      "nagaai": {
        "baseUrl": "https://api.naga.ac/v1",
        "apiKey": "YOUR_API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "gpt-5.2",
            "name": "GPT 5.2 (Naga)",
            "api": "openai-completions",
            "reasoning": false,
            "input": ["text", "image"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 200000,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "nagaai/gpt-5.2"
      },
      "models": {
        "nagaai/gpt-5.2": {
          "alias": "gpt"
        }
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }
}
Keep real API keys out of version control.
3

Apply the config

Apply the updated file (restart OpenClaw after applying if needed):
openclaw gateway config.apply --file ~/.openclaw/openclaw.json

​
Notes

  • Base URL must include /v1: https://api.naga.ac/v1
  • The model name in OpenClaw uses the provider prefix: nagaai/gpt-5.2
  • NagaAI model list: https://naga.ac/models