Model Serving Pricing

• Total queries/total time determines number of concurrent requests required per hour
• 1 DBU/hr provides 1 concurrent request/hr; scales in increments of 4 DBU/hr

4 GB per concurrent request

Usage of these services will be appear on your bill under Serverless Real-time Inference

If the 'scale to zero' is not selected, the minimum charge will depend on the minimum provisioned concurrency specified by the chosen concurrency range.

If ‘scale to zero’ is selected, scale to zero happens automatically after 30 minutes of no requests, at which time the endpoint enters the fully scaled-to-zero (idle) state. You are not charged during this time period. When a new request is made, the endpoint exits this idle state and begins scaling up at which point you begin getting charged