GMI Cloud Provider: OpenAI-Compatible API Integration

GMI Cloud is a hosted inference platform that provides access to frontier and open-weight models through an OpenAI-compatible API. In OpenClaw it ships as an official external provider plugin: install it once, store credentials using standard model auth, and reference models with refs like gmi/google/gemini-3.1-flash-lite.

Choose GMI when you need a single API key for multiple hosted model families, including Anthropic, DeepSeek, Google, Moonshot, OpenAI, and Z.AI routes listed in GMI's catalog. It serves as a secondary provider for model fallback, for comparing hosted routes across vendors, or when GMI offers a model before your primary provider does. OpenClaw manages the provider id, auth profile, aliases, model catalog seed, and base URL; GMI handles live model availability, billing, rate limits, and any provider-side routing policy.

Setup

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

openclaw plugins install @openclaw/gmi-provider
openclaw gateway restart

Then run:

openclaw onboard --auth-choice gmi-api-key

Non-interactive setups can pass --gmi-api-key <key>, or set:

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

When to choose GMI

• You want a hosted OpenAI-compatible endpoint instead of running a local model server.
• You want to test multiple commercial and open-weight model families through a single provider account.
• You need a fallback provider with different upstream routing than DeepInfra, OpenRouter, Together, or the direct vendor APIs.
• You require 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 is more important than hosted convenience.

Models

The plugin catalog seeds commonly available GMI Cloud route ids:

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

openclaw models list --provider gmi

Troubleshooting

• 401 or 403: verify that GMI_API_KEY is set for the process running OpenClaw, 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 openclaw models list --provider gmi.
• Intermittent provider errors: try a different GMI route or configure GMI as a fallback instead of the only primary model provider.

Related

• Model providers
• All providers