Get an inference instance type
Retrieves the GPU resources, pricing, regional availability, and best-effort capacity headroom for one inference instance type.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Resource identifier.
Response
OK
GPU hardware configuration on which one inference replica can run.
Stable hardware instance type identifier used by deployment configs.
Human-readable instance type name.
Human-readable summary of the hardware configuration.
GPU accelerator model, such as H100 or B200.
Number of GPUs in one replica of this instance type.
Memory available on each GPU, in GiB.
On-demand price for one running replica, in US cents per hour.
Regions where this instance type is offered.