OpenCode Zen and Go Catalogs via OpenClaw

Learn how to use OpenCode's Zen and Go hosted catalogs through OpenClaw, including setup, model defaults, and verification. Essential for developers integrating OpenCode models.

Read this when

  • You want OpenCode-hosted model access
  • You want to pick between the Zen and Go catalogs

OpenCode provides two hosted catalogs through OpenClaw:

CatalogPrefixRuntime provider
Zenopencode/...opencode
Goopencode-go/...opencode-go

The two catalogs rely on the identical OpenCode API key setup (OPENCODE_API_KEY, alias OPENCODE_ZEN_API_KEY). A separate paid subscription remains necessary for Go; holding a Zen key alone does not automatically unlock Go. OpenClaw maintains distinct runtime provider ids so that upstream per-model routing continues to function properly.

Getting started

Zen catalog

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

Run onboarding

openclaw onboard --auth-choice opencode-zen

The key can also be supplied directly:

openclaw onboard --opencode-zen-api-key "$OPENCODE_API_KEY"

Set a Zen model as the default

openclaw config set agents.defaults.model.primary "opencode/gpt-5.6-sol"

Verify models are available

openclaw models list --provider opencode

Go catalog

Best for: the separately subscribed Go lineup across DeepSeek, GLM, GPT, Grok, Hy3, Kimi, MiMo, MiniMax, and Qwen.

Use the bundled Go catalog

For this release, OpenClaw ships with OpenCode Go already included, so no extra plugin installation or Gateway restart is needed.

Run onboarding

openclaw onboard --auth-choice opencode-go

Alternatively, pass the key straight through:

openclaw onboard --opencode-go-api-key "$OPENCODE_API_KEY"

Set a Go model as the default

openclaw config set agents.defaults.model.primary "opencode-go/kimi-k3"

Verify models are available

openclaw models list --provider opencode-go

Config example

{
  env: { vars: { OPENCODE_API_KEY: "sk-..." } },
  agents: { defaults: { model: { primary: "opencode/gpt-5.6-sol" } } },
}

Provider catalogs

Zen

PropertyValue
Runtime provideropencode
Example modelsopencode/gpt-5.6-sol, opencode/kimi-k3, opencode/deepseek-v4-flash

Execute openclaw models list --provider opencode to see the currently active list. Model availability and promotional routes may shift independently of OpenClaw.

Live discovery merges the models accessible to your OpenCode account with authoritative model metadata sourced from https://models.opencode.ai/api.json. OpenClaw retrieves and caches that catalog only when OpenCode Zen or Go is enabled or explicitly chosen with OpenCode credentials; startup and unrelated providers never trigger the download. New upstream models appear without an OpenClaw update as long as their metadata specifies a supported transport on the trusted OpenCode endpoint. A response scoped to a key can omit models unavailable to that workspace. Metadata and lifecycle status refresh in tandem; deprecated models are left out of active discovery and its offline fallback. Deprecated explicit refs stay resolvable for existing configurations but are no longer presented as current recommendations.

Go

PropertyValue
Runtime provideropencode-go
Example modelsopencode-go/kimi-k3, opencode-go/deepseek-v4-flash, opencode-go/qwen3.8-max

Refer to OpenCode Go for discovery, routing, and access requirements. The model-list endpoint for Go advertises its general lineup; a model being listed does not guarantee your account can execute it.

Advanced configuration

API key aliases

As an alias for OPENCODE_API_KEY, OPENCODE_ZEN_API_KEY is also recognized.

Shared credentials

During setup, a single OpenCode key entry can store credentials for both runtime providers. That action does not establish a Go subscription or confer Go entitlement; subscribe to Go in the OpenCode console before using it.

Getting an API key

Set up an OpenCode account and obtain an API key at opencode.ai/auth. Billing and catalog availability are handled from the OpenCode dashboard.

Gemini replay behavior

OpenCode refs backed by Gemini remain on the proxy-Gemini path, so OpenClaw applies Gemini thought-signature sanitation there without enabling native Gemini replay validation or bootstrap rewrites.

Non-Gemini replay behavior

Non-Gemini OpenCode refs retain the minimal OpenAI-compatible replay policy.

Pricing and privacy

Billing, retention, and training policies differ by model. Review the current OpenCode Zen pricing and policy before picking a route. Free models may represent temporary feedback programs.

685 words · updated Sep 1, 2026