cURL
curl --request GET \ --url https://api.example.com/inference/nvidia/v2/hardware \ --header 'Authorization: Bearer <token>'
{ "hardware": [ { "id": "<string>", "name": "<string>", "type": "<string>", "pricing": { "cents_per_million_input_tokens": 123, "cents_per_million_output_tokens": 123 }, "specs": {} } ] }
Returns available hardware and pricing for a given model.
Called by NVIDIA to show users their options and redirect them based on what we support. Only serverless options are returned.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Bearer <token>
<token>
Model name without the publisher prefix
Successful Response
Show child attributes
Was this page helpful?