GMI Cloud
A RocketRide LLM node that connects GMI Cloud-hosted models to a pipeline through GMI Cloud's OpenAI-compatible API.
About GMI Cloud
GMI Cloud is a cloud platform for deploying and serving AI models through managed inference endpoints. Its catalog includes open-weight models and access to models from multiple providers.
What it does
Connects GMI Cloud-hosted models to a pipeline via an OpenAI-compatible API. Use it
as an llm invoke connection for agents and other nodes that need an LLM, or wire
it directly through the question and answer lanes.
Built on langchain-openai's ChatOpenAI client pointed at the GMI Cloud endpoint,
with temperature fixed at 0. Rate-limit and connection errors are treated as
retryable; authentication and other API errors are mapped to friendly messages
(e.g. Invalid API key.).
Two safety behaviors are enforced on the endpoint URL: it must use HTTPS, and the
hostname must be gmi-serving.com or a subdomain of it (an SSRF guard on user-supplied
endpoints). This is checked both at save time and when the pipeline starts. An API key is
required at pipeline start; the shared endpoint https://api.gmi-serving.com/v1 is used
when no endpoint URL is configured.
Lanes
| Lane in | Lane out | Description |
|---|---|---|
questions | answers | Send a question directly, receive a generated answer |
Profiles
Default: DeepSeek V3 (deepseek-v3).
| Profile | Model | Context tokens |
|---|---|---|
| DeepSeek V3 (default) | deepseek-ai/DeepSeek-V3-0324 | 163,840 |
| Gemini 3.1 Pro | google/gemini-3.1-pro-preview | 128,000 |
| Gemini 3.1 Flash Lite | google/gemini-3.1-flash-lite-preview | 128,000 |
| GPT-5.2 | openai/gpt-5.2 | 128,000 |
View 18 more models
| Profile | Model | Context tokens |
|---|---|---|
custom | (user-specified) | editable |
| Llama 4 Scout | meta-llama/Llama-4-Scout-17B-16E-Instruct | 1,048,576 |
| Llama 4 Maverick | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1,048,576 |
| Qwen3 235B | Qwen/Qwen3-235B-A22B-FP8 | 131,072 |
| Qwen3 32B | Qwen/Qwen3-32B-FP8 | 131,072 |
| Qwen3 30B | Qwen/Qwen3-30B-A3B | 131,072 |
| Qwen3 Coder 480B | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | 131,072 |
| DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | 163,840 |
| DeepSeek R1 | deepseek-ai/DeepSeek-R1 | 131,072 |
| DeepSeek R1 Distill 32B | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 131,072 |
| DeepSeek R1 Distill 1.5B | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | 131,072 |
| DeepSeek Prover V2 | deepseek-ai/DeepSeek-Prover-V2-671B | 131,072 |
| GPT-5.1 | openai/gpt-5.1 | 128,000 |
| GPT-5 | openai/gpt-5 | 128,000 |
| GPT-4o | openai/gpt-4o | 128,000 |
| Claude Opus 4.5 | anthropic/claude-opus-4.5 | 200,000 |
| Claude Sonnet 4.5 | anthropic/claude-sonnet-4.5 | 200,000 |
| Gemini 3 Flash | google/gemini-3-flash-preview | 128,000 |
Configuration
Choose a profile for a shared or deployed model. Named profiles set the model and context limit; shared models also use the default endpoint, so most pipelines only need an API key.
Endpoint URL
Deploy-on-demand profiles require the endpoint supplied by the GMI Cloud console.
The URL must use HTTPS and its hostname must be gmi-serving.com or a subdomain;
other hosts are rejected. The shared endpoint defaults to
https://api.gmi-serving.com/v1.
Custom models
Select custom to provide a GMI Cloud model identifier, its context limit, its
output limit (4,096 by default), and an endpoint URL directly. Open-weight identifiers use org/model-name, such as
deepseek-ai/DeepSeek-R1; proxied identifiers use provider/model-name, such as
openai/gpt-4o.
Authentication
Provide a GMI Cloud API key in the API Key field. That is sufficient for shared-tier models. For deploy-on-demand models, deploy the model in the GMI Cloud console and also provide the unique endpoint URL.
Notes
Model tiers
Shared models are available immediately at the shared endpoint with an API key. Llama, Qwen, and R1 Distill profiles are deploy-on-demand and require an endpoint created in the GMI Cloud console. The custom profile accepts any GMI Cloud model ID, token limit, and endpoint URL directly.
Save-time validation
When the node configuration is saved, it is validated against the live API:
- Validation is skipped when the model or API key is not set yet.
- A deploy-on-demand profile whose endpoint URL is still empty is reported right there: the pipeline could not start without it, and the message belongs next to the field, not at run time.
- The endpoint URL is checked for HTTPS and the
gmi-serving.comdomain. - If the model name looks like a vision/multimodal model (contains
vl,vision,visual, ormultimodal), a warning is raised suggesting a vision node instead, and the API probe is skipped, since vision models may reject text-only requests. - Otherwise a 1-token chat request probes the API to confirm both the API key and the model's existence. An HTTP 429 (rate limit) during the probe means the key was accepted and is treated as valid. Other API errors surface as warnings with the HTTP status, provider error type, and message.
Model sync
Profiles are maintained by the sync_models tooling (llm_gmi_cloud provider,
ROCKETRIDE_GMI_CLOUD_KEY), which reads GMI Cloud's own model list.
A profile the sync adds carries the shared endpoint
(https://api.gmi-serving.com/v1), since that is where discovery verified the
model answers. Selecting it needs only an API key. A deploy-on-demand model
still requires the endpoint URL from the GMI Cloud console.
Token limits come from GMI Cloud itself, with one exception: for the models GMI
resells rather than hosts (openai/…, anthropic/…, google/…), the vendor's
published limits apply, so those profiles track llm_openai, llm_anthropic and
llm_gemini. For a model GMI runs on its own hardware, the context window is
GMI's choice, and no third-party database can state it: OpenRouter and LiteLLM
list the same open-weight model with different windows per host.
For the same reason the sync runs only with that key. GMI's IDs
(Qwen/Qwen3-32B-FP8) appear in no other catalogue, so a keyless run would mark
every profile here deprecated. Without the key the provider is skipped and
nothing changes — see Why some providers need their own key.
Upstream docs
Schema
| Field | Type | Description | Default |
|---|---|---|---|
gmi_cloud.profile | string | Model GMI Cloud LLM model | "deepseek-v3" |
gmi_cloud.serverbase | string | Endpoint URL Your GMI Cloud deployment endpoint URL. Deploy the model at console.gmicloud.ai, then paste the provided endpoint URL here. | |
model | string | Model GMI Cloud model identifier. Use org/model-name for open-weight models (e.g. deepseek-ai/DeepSeek-R1, Qwen/Qwen3-32B-FP8) or provider/model-name for proxied models (e.g. openai/gpt-4o, anthropic/claude-sonnet-4.5, google/gemini-3-flash-preview). Full list: https://www.gmicloud.ai/models | |
modelOutputTokens | integer | Output Tokens Most tokens the model may write in one reply (at least 1,024). Leave it empty to keep the node's default. Reasoning models count their thinking against this limit: set it well above the reply you expect, or they can spend it all thinking and return nothing. It cannot exceed Tokens; a larger value is lowered to it. | |
modelTotalTokens | number | Tokens Total Tokens |
Dependencies
openailangchain-openailangchain-corelangchain