List available hardware configurations
Returns a list of available hardware configurations for deploying models. When a model parameter is provided, it returns only hardware configurations compatible with that model, including their current availability status.
Authorization
bearerAuth In: header
Query Parameters
Filter hardware configurations by model compatibility. When provided, the response includes availability status for each compatible configuration. See all of Together AI's dedicated models
Response Body
application/json
application/json
application/json
curl -X GET "https://example.com/hardware"{ "object": "list", "data": [ { "object": "hardware", "id": "2x_nvidia_a100_80gb_sxm", "pricing": { "cents_per_minute": 5.42 }, "specs": { "gpu_type": "a100-80gb", "gpu_link": "sxm", "gpu_memory": 80, "gpu_count": 2 }, "availability": { "status": "available" }, "updated_at": "2019-08-24T14:15:22Z" } ]}Remove a LoRA adapter from an endpoint DELETE
Removes the routing rule that binds an adapter to an endpoint. The adapter must be currently bound to this specific endpoint.
Execute code POST
Executes the given code snippet and returns the output. Without a session_id, a new session is created to run the code. If you pass a valid session_id, the code runs in that session. This is useful for running multiple code snippets in the same environment, because dependencies and similar things are persisted between calls to the same session.