GMI Cloud is a hosted inference platform for frontier and open-weight models behind an OpenAI-compatible API. In Apus it is an official external provider plugin: install it once, store credentials through normal model auth, and use model refs like gmi/openai/gpt-5.6-sol.

Use GMI when you want one API key for several hosted model families, including Anthropic, DeepSeek, Google, Moonshot, OpenAI, and Z.AI routes exposed by GMI's catalog. It works as a secondary provider for model fallback, for comparing hosted routes across vendors, or when GMI has a model available before your primary provider does. Apus owns the provider id, auth profile, aliases, model catalog seed, and base URL; GMI owns live model availability, billing, rate limits, and any provider-side routing policy.

Setup

Install the plugin, then create an API key in GMI Cloud (https://www.gmicloud.ai/):

apus plugins install @openclaw/gmi-provider

Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

Then run:

apus onboard --auth-choice gmi-api-key

For scripted or CI installs, pass everything on the command line:

apus onboard --non-interactive --accept-risk --skip-health \
  --auth-choice gmi-api-key \
  --gmi-api-key "$GMI_API_KEY"

Or set the key in the environment instead:

export GMI_API_KEY="<your-gmi-api-key>" # pragma: allowlist secret

When to choose GMI

• You want a hosted OpenAI-compatible endpoint rather than a local model server.
• You want to try several commercial and open-weight model families through one provider account.
• You want a fallback provider with different upstream routing from DeepInfra, OpenRouter, Together, or the direct vendor APIs.
• You need GMI-specific model ids, pricing, or account controls.

Choose the direct vendor provider instead when you need vendor-native features that GMI does not expose through its OpenAI-compatible route. Choose a local provider such as LM Studio, Ollama, SGLang, or vLLM when data locality or local GPU control matters more than hosted convenience.

Models

OpenAI tool turns automatically use reasoning_effort: "none" for GPT-5.6 and omit the field for GPT-5.5 and GPT-5.4 mini.

The plugin catalog seeds commonly available GMI Cloud route ids:

The catalog is a seed, not a promise that every account can call every model at all times. List what the configured provider reports in your environment:

apus models list --provider gmi

Troubleshooting

• 401 or 403: check that GMI_API_KEY is set for the process running Apus, or re-run onboarding to store the key in the provider auth profile.
• Unknown model errors: confirm the model exists in your GMI account and use the full gmi/<route-id> ref shown by apus models list --provider gmi.
• Intermittent provider errors: try a different GMI route or configure GMI as a fallback rather than the only primary model provider.

Related

• Model providers
• All providers