Instance Type Service
Get an inference instance type
Retrieves the GPU resources, pricing, regional availability, and best-effort capacity headroom for one inference instance type.
Authorization
bearerAuth AuthorizationBearer <token>
In: header
Path Parameters
id*string
Resource identifier.
Response Body
application/json
application/json
curl -X GET "https://example.com/public/inference-instance-types/string"{ "id": "string", "name": "string", "description": "string", "gpuType": "string", "gpuCount": 0, "gpuMemoryGib": 0, "priceCentsPerHour": 0, "regions": [ { "name": "string", "headroom": { "value": 0, "relation": "RELATION_EQ" }, "compliance": [ { "policy": { "hipaa": true }, "headroom": { "value": 0, "relation": "RELATION_EQ" } } ] } ]}List inference instance types GET
Lists hardware instance types currently available to inference deployments, including GPU resources, pricing, regions, and best-effort capacity headroom.
List supported models GET
Lists Together-hosted base models that can be deployed for dedicated inference, together with their capabilities and certified deployment profiles.