Integration · Pi

Use Verboo Code in Pi

Connect Verboo Code models to the Pi agent with a simple configuration.

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.

Install

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

How to connect

1
Create your API key
- Sign in to the Verboo Code dashboard and open API Keys in the sidebar.
- Click Create API Key, name it after the tool so you recognise it later, and pick the plan you will use.
- Copy the key right away: it is not shown again.
- The same screen lists the model IDs available to your plan — one of them replaces <MODEL_ID>.

Install Pi

Install the coding agent with npm.

npm

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

Add the Verboo provider

Create or merge this block into the models file. Replace <MODEL_ID> with an ID from your account's models page.

~/.pi/agent/models.json

{
  "providers": {
    "verboo": {
      "baseUrl": "https://code.verboo.ai/router/v1",
      "api": "openai-completions",
      "apiKey": "$VERBOO_API_KEY",
      "authHeader": true,
      "models": [
        {
          "id": "<MODEL_ID>"
        }
      ]
    }
  }
}

4
Start with the Verboo model
- Export VERBOO_API_KEY with your key and start Pi selecting the provider.
CLI
```
pi --provider verboo --model "<MODEL_ID>"
```