Skip to main content
Create a new serverless endpoint that can execute your AI models on-demand. Endpoints are created from templates and can be scaled with multiple workers.

​
Required Parameters

  • name: Human-readable name for the endpoint (1-100 characters)
  • templateId: ID of the template to use for the endpoint
  • gpuIds: Array of GPU IDs to allocate to the endpoint

​
Optional Parameters

  • workerCount: Number of workers (1-10, default: 1)

​
Example Usage

curl -X POST "https://api.tensorone.ai/v2/endpoints" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-image-generator",
    "templateId": "tpl_stable_diffusion_xl",
    "gpuIds": ["gpu_nvidia_a100_1"],
    "workerCount": 2
  }'

​
Response

Returns the created endpoint object: 
{
    "id": "ep_1234567890abcdef",
    "name": "my-image-generator",
    "status": "pending",
    "url": "https://api.tensorone.ai/v2/ep_1234567890abcdef/runsync",
    "templateId": "tpl_stable_diffusion_xl",
    "gpuType": "NVIDIA A100",
    "createdAt": "2024-01-15T10:30:00Z",
    "updatedAt": "2024-01-15T10:30:00Z"
}
Endpoint creation is asynchronous. The endpoint will show pending status while being provisioned, then transition to active when ready to accept requests.