Integration · OpenClaw

Use Verboo Code in OpenClaw

Add Verboo Code as an OpenAI-compatible provider and choose the model available to your plan.

Start for free Technical documentation

Unlimited tokens

Paid plans have no token cap. What exists is a per-minute rate limit, because heavier models need more GPU.

Fixed price per developer

You know what you pay at the end of the month. An agent running all night does not become a surprise invoice.

Works with what you have

An OpenAI-compatible endpoint: swap the base URL and the key, keep your workflow.

How to connect

1
Choose a model
- The model list is specific to your API key. Check it before creating the configuration and replace <MODEL_ID> with a returned ID.
List models
```
curl https://code.verboo.ai/router/v1/models \
  -H "Authorization: Bearer <VERBOO_API_KEY>"
```

Add the provider

Add this block to your OpenClaw configuration file. Preserve existing providers when merging it.
Open your OpenClaw config file (~/.openclaw/openclaw.json)
Merge the verboo provider into the models.providers section
The Gateway hot-reloads config changes automatically. Restart if needed.

~/.openclaw/openclaw.json

{
  "models": {
    "mode": "merge",
    "providers": {
      "verboo": {
        "baseUrl": "https://code.verboo.ai/router/v1",
        "api": "openai-completions",
        "apiKey": "<VERBOO_API_KEY>",
        "models": [
          {
            "id": "<MODEL_ID>",
            "name": "Verboo Code",
            "contextWindow": <CONTEXT_WINDOW>,
            "reasoning": <REASONING_ENABLED>,
            "input": ["text", "image"]
          }
        ]
      }
    }
  }
}

3
Select and use
- After saving, select the model from the Verboo provider in OpenClaw. Restart the Gateway if your version does not reload the configuration automatically.
- Open the model picker and select Verboo Code. If it doesn't appear, run: openclaw models set verboo-model
Select the model
```
openclaw models set verboo-model
```

Verify

You can now start a conversation normally. OpenClaw sends Chat Completions to the Verboo Code Router.

Fill in model capabilities

Copy context_window into contextWindow. Set reasoning: true only when the reasoning object exists. Keep image in input only when vision is true; otherwise use ["text"].

Do not version your key

The example uses a placeholder. In shared environments, prefer OpenClaw secrets or environment variable support.