Deploy a GPU | EmpirioLabs AI Docs

Start a GPU Cloud instance. Choose a curated model, paste any Hugging Face repo id (served with vLLM, OpenAI-compatible at /v1), pick a template (JupyterLab, ComfyUI, Web Terminal, Ollama), or run a custom Docker image. Billing starts when the GPU reaches running and is metered by the second against your credit balance. Your account’s current GPU limit is enforced at deploy and start time.

Start a GPU Cloud instance. Choose a curated model, paste any Hugging Face repo id (served with vLLM, OpenAI-compatible at `/v1`), pick a template (JupyterLab, ComfyUI, Web Terminal, Ollama), or run a custom Docker image. Billing starts when the GPU reaches `running` and is metered by the second against your credit balance. Your account's current GPU limit is enforced at deploy and start time.

Autenticación

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Solicitud

This endpoint expects an object.

gpu_slugstringRequerido

The GPU type to deploy from the catalog.

modeenumOpcional

How to provision the GPU.

hf_idstringOpcional

A Hugging Face repo id to serve with vLLM (mode model). Set HF_TOKEN in env for gated repos.

template_slugstringOpcional

A curated model or template slug (mode model or template).

imagestringOpcional

A CUDA Docker image to run (mode custom).

portslist of integersOpcional

Ports the workload listens on (mode custom).

envmap from strings to stringsOpcional

Environment variables for the workload.

num_gpusintegerOpcional1-64Valor predeterminado: 1

Number of GPUs. Your current account limit is enforced at deploy and start time.

disk_gbintegerOpcional100-300Valor predeterminado: 150

Requested runtime disk in GB (100-300).

namestringOpcional

Optional label for the GPU Cloud instance.

Respuesta

Instance accepted and provisioning.

instanceobject

Errores

402

Payment Required Error

404

Not Found Error

409

Conflict Error

422

Unprocessable Entity Error

$	curl -X POST https://api.empiriolabs.ai/v1/gpu/instances \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"gpu_slug": "rtx-4090"
>	}'

1	{
2	"instance": {
3	"id": "a3f1c9e2-7b4d-4f8a-9c2e-5d6f7a8b9c0d",
4	"status": "provisioning",
5	"gpu_slug": "rtx-4090",
6	"gpu_display": "RTX 4090",
7	"num_gpus": 1,
8	"image": "pytorch/pytorch:2.4.0-cuda12.1-cudnn9-runtime",
9	"label": "Deep Learning Instance",
10	"disk_gb": 150,
11	"price_hourly": 0.65,
12	"connect_path": "/v1",
13	"billed_amount": 0,
14	"created_at": "2024-01-15T09:30:00Z",
15	"started_at": "2024-01-15T09:30:00Z",
16	"error": ""
17	}
18	}