Skip to content

OpenCode Go

OpenCode Go is the Go catalog within OpenCode. It uses the same OPENCODE_API_KEY as the Zen catalog, but keeps the runtime provider id opencode-go so upstream per-model routing stays correct.

PropertyValue
Runtime provideropencode-go
AuthOPENCODE_API_KEY
Parent setupOpenCode

OpenClaw sources most Go catalog rows from the bundled pi model registry and supplements current upstream rows while the registry catches up. Run openclaw models list --provider opencode-go for the current model list.

The provider includes:

Model refName
opencode-go/glm-5GLM-5
opencode-go/glm-5.1GLM-5.1
opencode-go/kimi-k2.5Kimi K2.5
opencode-go/kimi-k2.6Kimi K2.6 (3x limits)
opencode-go/deepseek-v4-proDeepSeek V4 Pro
opencode-go/deepseek-v4-flashDeepSeek V4 Flash
opencode-go/mimo-v2-omniMiMo V2 Omni
opencode-go/mimo-v2-proMiMo V2 Pro
opencode-go/minimax-m2.5MiniMax M2.5
opencode-go/minimax-m2.7MiniMax M2.7
opencode-go/qwen3.5-plusQwen3.5 Plus
opencode-go/qwen3.6-plusQwen3.6 Plus
  1. Run onboarding

    Terminal window
    openclaw onboard --auth-choice opencode-go
  2. Set a Go model as default

    Terminal window
    openclaw config set agents.defaults.model.primary "opencode-go/kimi-k2.6"
  3. Verify models are available

    Terminal window
    openclaw models list --provider opencode-go
{
env: { OPENCODE_API_KEY: "YOUR_API_KEY_HERE" }, // pragma: allowlist secret
agents: { defaults: { model: { primary: "opencode-go/kimi-k2.6" } } },
}
Routing behavior

OpenClaw handles per-model routing automatically when the model ref uses opencode-go/.... No additional provider config is required.

Runtime ref convention

Runtime refs stay explicit: opencode/... for Zen, opencode-go/... for Go. This keeps upstream per-model routing correct across both catalogs.

Shared credentials

The same OPENCODE_API_KEY is used by both the Zen and Go catalogs. Entering the key during setup stores credentials for both runtime providers.

OpenCode (parent)

Shared onboarding, catalog overview, and advanced notes.

Model selection

Choosing providers, model refs, and failover behavior.