Create and manage CoreWeave Managed Inference capacity claims for Dedicated Inference. See capacity claims for capacity type details.
Example usage
Schema
Required
name (String) The name of the capacity claim. Must be a valid hostname label.
resources (Attributes) Resource configuration for the capacity claim. (see below for nested schema)
Read-Only
allocated_instances (Number) The number of instances currently allocated.
conditions (Attributes List) Detailed status conditions for the capacity claim. (see below for nested schema)
created_at (String) RFC3339 timestamp of when the capacity claim was created.
id (String) The unique identifier of the capacity claim.
organization_id (String) The organization ID that owns the capacity claim.
pending_instances (Number) The number of instances pending allocation.
status (String) The current status of the capacity claim. See the Inference API overview for status values.
updated_at (String) RFC3339 timestamp of when the capacity claim was last updated.
Nested Schema for resources
Required:
capacity_type (String) The capacity type for the capacity claim. Must be CAPACITY_TYPE_MANAGED.
instance_count (Number) The number of instances to reserve. Must be at least 1.
instance_type (String) The instance type to reserve (e.g. gb200-4x). Case-sensitive.
zones (Set of String) The availability zones where the capacity claim may use resources from (e.g. US-WEST-04A), case-sensitive. At least one is required.
Nested Schema for conditions
Read-Only:
last_update_time (String) RFC3339 timestamp of the last condition transition.
message (String) A human-readable message about the condition’s last transition.
reason (String) A short, machine-readable reason for the condition’s last transition.
status (String) The condition status (True, False, or Unknown).
type (String) The condition type (e.g. Ready, Progressing).
Import
Import is supported using the following syntax:
Last modified on September 29, 2026