Skip to main content
GMI Cloud is a hosted inference platform for frontier and open-weight models behind an OpenAI-compatible API. In OpenClaw it is an official external provider plugin: install it once, store credentials through normal model auth, and use model refs like gmi/google/gemini-3.1-flash-lite. 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. OpenClaw 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.
PropertyValue
Provider idgmi (aliases: gmi-cloud, gmicloud)
Package@openclaw/gmi-provider
Auth env varGMI_API_KEY
APIOpenAI-compatible (openai-completions)
Base URLhttps://api.gmi-serving.com/v1
Default modelgmi/google/gemini-3.1-flash-lite

​
Setup

Install the plugin, restart the gateway, then create an API key in GMI Cloud (https://www.gmicloud.ai/):
Then run:
Non-interactive setups can pass --gmi-api-key <key>, or set:

​
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

The plugin catalog seeds commonly available GMI Cloud route ids:
Model refInputContextMax output
gmi/anthropic/claude-sonnet-4.6text + image200,00064,000
gmi/deepseek-ai/DeepSeek-V3.2text163,84065,536
gmi/google/gemini-3.1-flash-litetext + image1,048,57665,536
gmi/moonshotai/Kimi-K2.5text + image262,14465,536
gmi/openai/gpt-5.4text + image400,000128,000
gmi/zai-org/GLM-5.1-FP8text202,75265,536
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:

​
Troubleshooting

  • 401 or 403: check 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 rather than the only primary model provider.