Connect Pi Coding Agent to APIONE

Install

Install the current Pi package using a supported Node.js version:

npm install -g @earendil-works/pi-coding-agent
pi --version
export APIONE_API_KEY="YOUR_APIONE_KEY"

Register the provider and model

Merge the following into ~/.pi/agent/models.json:

{
  "providers": {
    "apione": {
      "baseUrl": "https://api.apione.ai/v1",
      "api": "openai-completions",
      "apiKey": "$APIONE_API_KEY",
      "models": [
        {"id": "YOUR_APIONE_MODEL_ID", "name": "APIONE model"}
      ]
    }
  }
}

Replace the model placeholder. apiKey references an environment variable that must be available to the Pi process. Add further models to the models array as needed.

Select and test

pi --list-models apione
pi --provider apione --model YOUR_APIONE_MODEL_ID

You can also run /model inside Pi. Verify text generation, directory reading, and coding tasks separately.

Authentication

This guide uses an APIONE API Key. Another service’s OAuth extension, browser authorization, and automatic model discovery do not become APIONE features by changing the provider name. Register models explicitly in this configuration and manage keys in the APIONE console. For missing models, check JSON syntax, the provider name, and models array. For 401, check the exported variable. For tool errors, check the protocol and model capabilities.

Integration directory · Choose a model · Troubleshooting

Integration guides

Coding assistants and CLI

Chat and workflows

Agent deployment

Network and authentication

Connect Pi Coding Agent to APIONE

Install

Register the provider and model

Select and test

Authentication