How to View Serverless Inference Metrics

Last verified 7 Oct 2026

Inference provides a single control plane for managing inference workflows. It includes a Model Catalog where you can view available foundation models, including both DigitalOcean-hosted and third-party commercial models, compare model capabilities and pricing, use routing to match inference requests to the best-fit model, and run inference using serverless or dedicated deployments.

Copy page as Markdown View page as Markdown

Inference observability provides real-time and historical metrics across latency, throughput, error rates, token consumption, cost attribution, and rate limiting. To view the metrics, in the DigitalOcean Control Panel, click INFERENCE ENGINE in the left menu, and then click Serverless Inference. Then, select the Analyze tab to view the metrics.

Page showing total tokens, token usage and other serverless inference metrics.

To see the estimated cost of individual Serverless Inference requests by model and model access key, use Serverless Inference Live Usage on the Cost Analysis tab of the Billing page.

We can't find any results for your search.

Try using different keywords or simplifying your search terms.