Skip to main content
OpenCode exposes two hosted catalogs in OpenClaw: Both catalogs share one OpenCode API key (OPENCODE_API_KEY, alias OPENCODE_ZEN_API_KEY). OpenClaw keeps the runtime provider ids split so upstream per-model routing stays correct, but onboarding and docs treat them as one OpenCode setup.

Getting started

Best for: the curated OpenCode multi-model proxy (Claude, GPT, Gemini, GLM, DeepSeek, Kimi, MiniMax, Qwen).
1

Run onboarding

Or pass the key directly:
2

Set a Zen model as the default

3

Verify models are available

Config example

Built-in catalogs

Zen

Run openclaw models list --provider opencode for the full current list, which also includes free-tier rows such as opencode/big-pickle and opencode/deepseek-v4-flash-free.

Go

See OpenCode Go for the full Go model table.

Advanced configuration

OPENCODE_ZEN_API_KEY is also accepted as an alias for OPENCODE_API_KEY.
Entering one OpenCode key during setup stores credentials for both runtime providers. You do not need to onboard each catalog separately.
Create an OpenCode account and generate an API key at opencode.ai/auth. Billing and catalog availability are managed from the OpenCode dashboard.
Gemini-backed OpenCode refs stay on the proxy-Gemini path, so OpenClaw keeps Gemini thought-signature sanitation there without enabling native Gemini replay validation or bootstrap rewrites.
Non-Gemini OpenCode refs keep the minimal OpenAI-compatible replay policy.

OpenCode Go

Full Go catalog reference.

Model selection

Choosing providers, model refs, and failover behavior.

Configuration reference

Full config reference for agents, models, and providers.