OpenCode
Details for running the OpenCode harness inside Conductor
OpenCode is an open source AI coding harness. It supports many LLM providers, including OpenRouter, Baseten, Cerebras, and Vercel AI Gateway. These providers give OpenCode access to open-source and frontier models.
OpenCode quick facts
| Topic | OpenCode |
|---|---|
| Availability | Conductor includes a managed OpenCode executable. You can use your own OpenCode install instead. |
| Setup | Settings -> Harnesses -> OpenCode for provider keys, visible models, and the OpenCode executable path. |
| Models | Models returned by your OpenCode providers, including open-source and frontier models. |
| Billing | The selected OpenCode provider, local model, ChatGPT, or GitHub Copilot. |
| Controls | Skills are supported. Plan Mode, Fast Mode, goals, and checkpoints are not supported today. |
Setup notes
Conductor includes a managed OpenCode executable. To use your own OpenCode install instead, set a custom executable path in OpenCode settings.
Settings -> Harnesses -> OpenCode shows provider status, provider API keys, visible models, and the custom OpenCode executable path.
Conductor can use provider keys from:
- OpenCode provider API keys saved in Conductor, including keys for providers such as OpenRouter, Baseten, Cerebras, and Vercel AI Gateway
- local environment variables detected from your shell or Conductor environment settings
- OpenCode provider configuration outside Conductor
See the OpenCode provider docs for providers or setup details that Conductor does not surface directly.
For a setup walkthrough, see Configure model providers: OpenCode.
Model access
Conductor asks OpenCode for the models available to your provider configuration. If you are not seeing models you expect: start by checking your executable, provider credentials, and OpenCode config.
OpenCode model IDs are provider-qualified, such as anthropic/claude-sonnet-4-5 or openai/gpt-5.1. Conductor labels those as provider/model choices in the model picker.