create_serverless_inference
Deploy serverless AI inference endpoints for scalable model hosting without managing infrastructure, using descriptive labels for organization.
Instructions
Create a new serverless inference subscription.
Args: label: A descriptive label for the inference subscription (e.g., "production-chatbot", "dev-testing")
Returns: Created inference subscription with ID, API key, and configuration details
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| label | Yes |
Input Schema (JSON Schema)
{
"properties": {
"label": {
"title": "Label",
"type": "string"
}
},
"required": [
"label"
],
"type": "object"
}