Runcrate · Schema
InstanceCreateRequest
Provide either `gpu_type` (Runcrate picks an available configuration for that GPU) or `instance_type_id` (specific config from `/instances/types`).
Artificial IntelligenceGPUInferenceComputePlatform
Properties
| Name | Type | Description |
|---|---|---|
| name | string | Human-readable instance name. |
| gpu_type | string | GPU model id (e.g. `h100-sxm`). Required if `instance_type_id` is not provided. |
| instance_type_id | string | Exact instance-type id from `GET /instances/types`. Required if `gpu_type` is not provided. |
| region | string | Only launch in this region: a `region` from `GET /instances/types`, the start of one (`us-east`), or a city or country (`canada`). If nothing is available there the request fails and names the regions |
| gpu_count | integer | |
| cpu_cores | integer | |
| memory | integer | GB |
| storage | integer | GB ephemeral storage |
| template | string | Template id to boot from. |
| ssh_key_id | string | ID of an SSH key to inject (create one via POST /ssh-keys). |
| env_vars | array | Environment variables to inject. Each item must be `{ "key": "NAME", "value": "..." }`. |
| startup_commands | array | |
| storage_id | string | Persistent volume to attach at boot. Mounts at `/workspace`. |
| launch_script | string | Raw shell script to run on boot. |
| launch_script_base64 | string | Base64-encoded launch script (alternative to `launch_script`). |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/runcrate/main/json-schema/runcrate-instance-create-request-schema.json",
"title": "InstanceCreateRequest",
"description": "Provide either `gpu_type` (Runcrate picks an available configuration for that GPU) or `instance_type_id` (specific config from `/instances/types`).",
"x-generated": "2026-10-21",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/_original/runcrate-api-openapi.json#/components/schemas/InstanceCreateRequest",
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Human-readable instance name."
},
"gpu_type": {
"type": "string",
"description": "GPU model id (e.g. `h100-sxm`). Required if `instance_type_id` is not provided."
},
"instance_type_id": {
"type": "string",
"description": "Exact instance-type id from `GET /instances/types`. Required if `gpu_type` is not provided."
},
"region": {
"type": "string",
"description": "Only launch in this region: a `region` from `GET /instances/types`, the start of one (`us-east`), or a city or country (`canada`). If nothing is available there the request fails and names the regions that have it; it never launches elsewhere. Defaults to `auto` (any region)."
},
"gpu_count": {
"type": "integer",
"minimum": 1
},
"cpu_cores": {
"type": "integer",
"minimum": 1
},
"memory": {
"type": "integer",
"description": "GB",
"minimum": 1
},
"storage": {
"type": "integer",
"description": "GB ephemeral storage",
"minimum": 1
},
"template": {
"type": "string",
"description": "Template id to boot from."
},
"ssh_key_id": {
"type": "string",
"description": "ID of an SSH key to inject (create one via POST /ssh-keys)."
},
"env_vars": {
"type": "array",
"items": {
"$ref": "#/$defs/EnvVar"
},
"description": "Environment variables to inject. Each item must be `{ \"key\": \"NAME\", \"value\": \"...\" }`."
},
"startup_commands": {
"type": "array",
"items": {
"type": "string"
}
},
"storage_id": {
"type": "string",
"description": "Persistent volume to attach at boot. Mounts at `/workspace`."
},
"launch_script": {
"type": "string",
"description": "Raw shell script to run on boot."
},
"launch_script_base64": {
"type": "string",
"description": "Base64-encoded launch script (alternative to `launch_script`)."
}
},
"$defs": {
"EnvVar": {
"type": "object",
"required": [
"key",
"value"
],
"properties": {
"key": {
"type": "string"
},
"value": {
"type": "string"
}
}
}
}
}
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/runcrate-instance-create-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
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.