Scale AI · Schema
CreateModelEndpointV1Request
Data EngineLabelingRLHFGenAI PlatformDonovanDefense AILiDARSensor FusionREST API
Properties
| Name | Type | Description |
|---|---|---|
| name | string | |
| model_bundle_id | string | |
| endpoint_type | object | |
| metadata | object | |
| post_inference_hooks | object | |
| cpus | object | |
| gpus | integer | |
| memory | object | |
| gpu_type | object | |
| storage | object | |
| nodes_per_worker | integer | |
| optimize_costs | object | |
| min_workers | integer | |
| max_workers | integer | |
| per_worker | integer | |
| concurrent_requests_per_worker | object | |
| forwarder_max_concurrency | object | Max in-flight requests admitted by the HTTP forwarder container, independent of `per_worker` / autoscaling. When None (default), the forwarder inherits its `--concurrency` flag from `per_worker` (curr |
| labels | object | |
| prewarm | object | |
| high_priority | object | |
| billing_tags | object | |
| default_callback_url | object | |
| default_callback_auth | object | |
| public_inference | object | |
| queue_message_timeout_seconds | object | For async endpoints, the queue message visibility/lock timeout in seconds. Controls how long a worker has to process a message before it becomes visible again (SQS VisibilityTimeout / ASB lock_duratio |
| task_expires_seconds | object | For async endpoints, how long a task can wait in queue before expiring (in seconds). Default: 86400 (24 hours). |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/scale-ai/json-schema/scale-ai-create-model-endpoint-v1-request-schema.json",
"title": "CreateModelEndpointV1Request",
"x-generated": "2026-10-27",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/scale-ai-llm-engine-openapi.yml#/components/schemas/CreateModelEndpointV1Request",
"properties": {
"name": {
"type": "string",
"maxLength": 63,
"title": "Name"
},
"model_bundle_id": {
"type": "string",
"title": "Model Bundle Id"
},
"endpoint_type": {
"$ref": "#/$defs/ModelEndpointType"
},
"metadata": {
"additionalProperties": true,
"type": "object",
"title": "Metadata"
},
"post_inference_hooks": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Post Inference Hooks"
},
"cpus": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
],
"title": "Cpus"
},
"gpus": {
"type": "integer",
"minimum": 0.0,
"title": "Gpus"
},
"memory": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
],
"title": "Memory"
},
"gpu_type": {
"anyOf": [
{
"$ref": "#/$defs/GpuType"
},
{
"type": "null"
}
]
},
"storage": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
}
],
"title": "Storage"
},
"nodes_per_worker": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Nodes Per Worker",
"default": 1
},
"optimize_costs": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Optimize Costs"
},
"min_workers": {
"type": "integer",
"minimum": 0.0,
"title": "Min Workers"
},
"max_workers": {
"type": "integer",
"minimum": 0.0,
"title": "Max Workers"
},
"per_worker": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Per Worker"
},
"concurrent_requests_per_worker": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0.0
},
{
"type": "null"
}
],
"title": "Concurrent Requests Per Worker"
},
"forwarder_max_concurrency": {
"anyOf": [
{
"type": "integer",
"maximum": 20.0,
"exclusiveMinimum": 0.0
},
{
"type": "null"
}
],
"title": "Forwarder Max Concurrency",
"description": "Max in-flight requests admitted by the HTTP forwarder container, independent of `per_worker` / autoscaling. When None (default), the forwarder inherits its `--concurrency` flag from `per_worker` (current behavior). Upper bound matches LIRA's FORWARDER_MAX_CONCURRENCY_LIMIT."
},
"labels": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Labels"
},
"prewarm": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Prewarm"
},
"high_priority": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "High Priority"
},
"billing_tags": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Billing Tags"
},
"default_callback_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Default Callback Url"
},
"default_callback_auth": {
"anyOf": [
{
"$ref": "#/$defs/CallbackAuth"
},
{
"type": "null"
}
]
},
"public_inference": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Public Inference",
"default": false
},
"queue_message_timeout_seconds": {
"anyOf": [
{
"type": "integer",
"maximum": 43200.0,
"minimum": 1.0
},
{
"type": "null"
}
],
"title": "Queue Message Timeout Seconds",
"description": "For async endpoints, the queue message visibility/lock timeout in seconds. Controls how long a worker has to process a message before it becomes visible again (SQS VisibilityTimeout / ASB lock_duration). Note: Azure Service Bus has a maximum of 300 seconds; values above this will be clamped."
},
"task_expires_seconds": {
"anyOf": [
{
"type": "integer",
"minimum": 1.0
},
{
"type": "null"
}
],
"title": "Task Expires Seconds",
"description": "For async endpoints, how long a task can wait in queue before expiring (in seconds). Default: 86400 (24 hours)."
}
},
"type": "object",
"required": [
"name",
"model_bundle_id",
"endpoint_type",
"metadata",
"cpus",
"gpus",
"memory",
"storage",
"min_workers",
"max_workers",
"per_worker",
"labels"
],
"$defs": {
"CallbackAuth": {
"oneOf": [
{
"$ref": "#/$defs/CallbackBasicAuth"
},
{
"$ref": "#/$defs/CallbackmTLSAuth"
}
],
"title": "CallbackAuth"
},
"CallbackBasicAuth": {
"properties": {
"kind": {
"type": "string",
"const": "basic",
"title": "Kind"
},
"username": {
"type": "string",
"title": "Username"
},
"password": {
"type": "string",
"title": "Password"
}
},
"type": "object",
"required": [
"kind",
"username",
"password"
],
"title": "CallbackBasicAuth"
},
"CallbackmTLSAuth": {
"properties": {
"kind": {
"type": "string",
"const": "mtls",
"title": "Kind"
},
"cert": {
"type": "string",
"title": "Cert"
},
"key": {
"type": "string",
"title": "Key"
}
},
"type": "object",
"required": [
"kind",
"cert",
"key"
],
"title": "CallbackmTLSAuth"
},
"GpuType": {
"type": "string",
"enum": [
"nvidia-tesla-t4",
"nvidia-ampere-a10",
"nvidia-ampere-a100",
"nvidia-ampere-a100e",
"nvidia-hopper-h100",
"nvidia-hopper-h100-1g20gb",
"nvidia-hopper-h100-3g40gb"
],
"title": "GpuType",
"description": "Lists allowed GPU types for Launch."
},
"ModelEndpointType": {
"type": "string",
"enum": [
"async",
"sync",
"streaming"
],
"title": "ModelEndpointType"
}
}
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/scale-ai-create-model-endpoint-v1-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.