Use LithosAI with OpenCode

Before you begin

Create a key on the API Keys page, confirm the model ID on the Models page, and export the key in the shell where you start OpenCode.

export LITHOSAI_API_KEY="your-key"

OpenCode reaches LithosAI directly, with no translation proxy or extra adapter. After you install OpenCode, declare the provider in opencode.json, either in a project or at ~/.config/opencode/opencode.json.

This connection uses OpenCode’s OpenAI-compatible Chat Completions adapter. Features that require another API protocol are not available through this provider configuration.

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "lithosai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LithosAI",
      "options": {
        "baseURL": "https://api.lithosai.cloud/v1",
        "apiKey": "{env:LITHOSAI_API_KEY}"
      },
      "models": {
        "moonshotai/Kimi-K3": { "name": "Kimi K3" },
        "moonshotai/Kimi-K3-fast": { "name": "Kimi K3 fast" }
      }
    }
  },
  "model": "lithosai/moonshotai/Kimi-K3"
}

@ai-sdk/openai-compatible is the package for Chat Completions providers, and OpenCode bundles it. Start OpenCode, then run /models to confirm that the LithosAI models appear.

opencode

Issues common to every agent are listed under Common issues.

Getting Started

Inference APIs

Account

Use LithosAI with OpenCode

Before you begin

​Before you begin

Before you begin