Install OpenCode using the official instructions. Run opencode, enter /connect, choose Other and use infistar as the provider ID. Enter your Infistar key. Create opencode.json in your project: 
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "infistar": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Infistar",
      "options": { "baseURL": "https://infistar.ai/v1" },
      "models": { "MODEL_ID": { "name": "MODEL_ID" } }
    }
  }
}
Replace MODEL_ID with a model available to the key. Restart OpenCode, enter /models and select it. The provider ID must match in /connect and the configuration.

​
Check the connection

Use an exact model ID available to your key, and begin with a short text request. For coding agents, first ask for a reply without reading or changing files or running commands. A successful text reply does not verify every tool or multimodal feature. For 401, check the key and its status. For 404, check the address and protocol. For model errors, recheck the model ID and selected group. See HTTP troubleshooting. Upstream documentation.