View usage
View usage in the dashboard, or query the same data through the Baseten CLI or Management API. Use the results for cost attribution, reporting, or spend alerts. The CLI and API separate dedicated inference, Model APIs, and training usage and include per-resource and daily breakdowns. A query can cover up to 31 days and cannot start before January 1, 2026 UTC.- UI
- Baseten CLI
- REST API
To view usage in the console:
- Sign in to your workspace at app.baseten.co and open Organization settings.
- Choose Billing and usage.
baseten org billing.
Account billing
Payment method
Baseten’s payment processor stores card and bank information. Baseten does not store it directly. To add or update a payment method:- Sign in to your workspace at app.baseten.co and open the billing dashboard.
- Choose Update payment method.
- Choose Card or US bank account and enter your information.
- Choose Save payment method.
Credits
New workspaces receive credits for testing and deployment. Baseten applies credits to the current invoice before charging a payment method; you do not need to redeem them. If the credits run out and the workspace has no payment method, Baseten deactivates its models until you add one. Baseten doesn’t offer a separate free tier or perpetual free plan. Baseten bills any usage beyond your starting credits at standard per-minute instance pricing. Check your current credit balance and remaining amount on the billing dashboard.If you signed up but don’t see credits applied to your workspace, or you’re evaluating Baseten for a larger proof of concept and need additional credits, contact us.
Invoices and payment cadence
Baseten issues an invoice when usage exceeds $50 or at the end of the calendar month, whichever comes first. After a history of successful payments, billing moves to a monthly cadence. You can view past invoices and payments in the billing dashboard. For questions about a specific invoice, contact support.Monthly budget
Set a monthly budget on the billing dashboard to receive spend notifications. The budget covers the workspace’s combined dedicated inference, Model APIs, and training usage for the calendar month. Baseten sends email notifications at 75%, 90%, and 100% of the budget. Changing a budget mid-month re-evaluates the thresholds against the new amount, and removing it turns budget notifications off entirely.Budget enforcement
By default, a budget sends notifications but does not stop usage. You remain responsible for costs above the configured amount. Enabling Enforce budget rejects Model API requests after spend reaches the budget. Access returns at the start of the next month, when you raise the budget above current spend, or when you remove the budget or disable enforcement. Enforcement applies only to Model APIs. A budget never stops dedicated deployments or training jobs; they continue to run and accrue charges regardless of this setting.Discounts
The Pro plan offers volume discounts. Education and nonprofit ML projects qualify for additional discounts. Contact support to apply.What’s billed
Baseten meters usage by the minute while a workload is running on a node. The instance’s per-minute price applies to serving replicas, image-builder workloads, and training workloads. Image builds are billable, but a replica that never starts is not. Baseten does not meter scheduling or image pulls before a workload starts, or draining, cleanup, and recycling after it terminates.Replica lifecycle
When you runtruss push, Baseten runs your image build as a workload and meters it the same way as serving replicas and training containers: from the moment the build comes up.
Cold starts are billable because model loading occurs after the replica starts. Setting min_replica to zero avoids GPU charges while idle, but the next request waits for a replica to start and load the model.
The full mapping:
The following details explain several lifecycle phases:
Why image build costs money. The build runs as its own workload, and Baseten meters it the same way as your serving replicas. Faster builds save money. Heavy or unnecessary install steps in your
config.yaml cost you on every push.
Why cold starts cost money. The replica is already up during model load, so those minutes count. See Cold starts for techniques to shrink that window.
Why failed boots are free. If the replica never comes up, you pay for zero minutes. Image-build failures that happen inside the builder workload, on the other hand, are billed up to the moment the build fails.
What happens if a replica dies mid-request. You pay for usage up to the moment the replica terminates, and partial minutes round up.