GMI Cloud Provider
기준일: 2026-07-26
난이도: 중급
공식 기준: GMI Cloud
개요
이 페이지는 OpenClaw GMI Cloud provider의 인증, 모델 ref, 온보딩 플래그, 설정 키를 공식 문서 기준으로 정리합니다.
공식 요약: Use GMI Cloud's OpenAI-compatible API with OpenClaw
model ref는 보통 provider/model 형식입니다. API key·endpoint·model id는 아래 원문 값을 그대로 쓰세요. 임의로 키나 엔드포인트를 만들지 마세요.
빠른 참조
| Property | Value |
|---|---|
| Provider id | gmi (aliases: gmi-cloud, gmicloud) |
| Package | @openclaw/gmi-provider |
| Auth env var | GMI_API_KEY |
| API | OpenAI-compatible (openai-completions) |
| Base URL | https://api.gmi-serving.com/v1 |
| Default model | gmi/google/gemini-3.1-flash-lite |
공식 문서 기반 상세
아래는 공식 providers/gmi 문서를 Mintlify 컴포넌트만 정리하고 공통 제목을 한국어로 맞춘 내용입니다. 설정 키, env, model ref, CLI 플래그는 원문 그대로 유지합니다.
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.
| Property | Value |
|---|---|
| Provider id | gmi (aliases: gmi-cloud, gmicloud) |
| Package | @openclaw/gmi-provider |
| Auth env var | GMI_API_KEY |
| API | OpenAI-compatible (openai-completions) |
| Base URL | https://api.gmi-serving.com/v1 |
| Default model | gmi/google/gemini-3.1-flash-lite |
설정
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 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.
모델
The plugin catalog seeds commonly available GMI Cloud route ids:
| Model ref | Input | Context | Max output |
|---|---|---|---|
gmi/anthropic/claude-sonnet-4.6 |
text + image | 200,000 | 64,000 |
gmi/deepseek-ai/DeepSeek-V3.2 |
text | 163,840 | 65,536 |
gmi/google/gemini-3.1-flash-lite |
text + image | 1,048,576 | 65,536 |
gmi/moonshotai/Kimi-K2.5 |
text + image | 262,144 | 65,536 |
gmi/openai/gpt-5.4 |
text + image | 400,000 | 128,000 |
gmi/zai-org/GLM-5.1-FP8 |
text | 202,752 | 65,536 |
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:
openclaw models list --provider gmi
문제 해결
401or403: check thatGMI_API_KEYis 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 byopenclaw 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.
관련 문서
검증 체크리스트
-
openclaw models list --provider gmi로 모델이 보이는지 확인 - 기본 model alias를
agents.defaults.model.primary에 설정했는지 확인 - API key / OAuth / 로컬 런타임 인증 경로를 공식 문서와 대조했는지 확인
- failover 시 데이터가 다른 provider로 이동할 수 있는지 검토