Use LithosAI with Pi

Before you begin

Install Pi CLI, create a key on the API Keys page, and choose a model on the Models page.

Set your API key

Export your key:

export LITHOSAI_API_KEY="your-key"

Configure LithosAI

The configuration uses deepseek-ai/DeepSeek-V4.1-Flash as an example.Add to ~/.pi/agent/models.json. Keep existing providers and set the token limits to match your model.

Pi configuration

~/.pi/agent/models.json

{
  "providers": {
    "lithosai": {
      "baseUrl": "https://api.lithosai.cloud/v1",
      "api": "openai-completions",
      "apiKey": "$LITHOSAI_API_KEY",
      "models": [
        {
          "id": "deepseek-ai/DeepSeek-V4.1-Flash",
          "name": "deepseek-ai/DeepSeek-V4.1-Flash",
          "reasoning": true,
          "contextWindow": 1048576,
          "maxTokens": 393216,
          "thinkingLevelMap": {
            "minimal": null,
            "low": "low",
            "medium": null,
            "high": "high",
            "xhigh": null,
            "max": "max"
          },
          "compat": {
            "thinkingFormat": "deepseek",
            "supportsReasoningEffort": true,
            "maxTokensField": "max_tokens"
          }
        }
      ]
    }
  }
}

"thinkingFormat": "deepseek" makes --thinking off send thinking: {"type": "disabled"}. Without it, Pi sends no thinking field when thinking is off, and the model thinks at its default effort high.To add another model or tier, copy the entry in providers.lithosai.models. Set id and name to the ID from the model catalog, and adjust contextWindow and maxTokens to match the model. Reopen Pi to load the changes.

Start a conversation

Run the following command:

pi --provider lithosai --model deepseek-ai/DeepSeek-V4.1-Flash --thinking high

Getting Started

Models

Inference APIs

Account

Use LithosAI with Pi

Before you begin

Model and reasoning effort

Resources

​Before you begin

​Model and reasoning effort

​Resources

Before you begin

Model and reasoning effort

Resources