Account billing
Payment method
Add or update payment details on the billing dashboard. Your card and bank information is stored with our payments processor, not by Baseten directly.Credits
New workspaces receive free credits for testing and deployment. Credits are applied automatically to your running invoice before any card charge, so there is nothing to redeem or activate. If your credits run out and you have not added a payment method, Baseten deactivates your models until you add one. Baseten does not offer a separate free tier or perpetual free plan. Usage beyond your starting credits is billed 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 support or reach out through baseten.co/talk-to-us.Invoices and payment cadence
Invoices are issued 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 get notified as spend accumulates. The budget is evaluated against your workspace’s total usage for the calendar month — dedicated deployments, Model APIs, and training combined — and warning emails are sent when usage reaches 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, setting a budget is informational only: usage continues past 100%, and you remain responsible for the costs. Checking Enforce budget rejects Model API requests once the budget is reached. Access to model APIs is restored at the start of the next month, or as soon as you raise the budget above the month’s spend so far, turn enforcement off, or remove the budget. Enforcement applies only to Model APIs. Dedicated deployments and training jobs are never stopped by a budget; they continue to run and bill regardless of this setting.Discounts
Volume discounts are available on the Pro plan. Education and nonprofit ML projects qualify for additional discounts. Contact support to apply.What’s billed
Baseten meters usage by the minute. For every minute a replica is observed as up on a node, the per-minute price for its instance type applies. The same rule covers the builder workload that produces your image after atruss push and the training workloads that run a fine-tune. The detail that catches people off guard: the builder counts, and failed boots do not.
What is not metered: anything that happens before a workload is observed as up (image pull onto the node, scheduling) or after it terminates (drain, cleanup, recycling).
Replica lifecycle
When you runtruss push, Baseten runs your image build as a workload. Like serving replicas and training containers, it is metered from the moment it is observed as up.
Cold starts are billed too. Model load happens after the replica is observed as up but before it is healthy enough to serve, so those minutes are on the bill. This is the cost side of the cold-start tradeoff: keeping min_replica at zero saves money during idle periods but pushes load time into your customer’s first request after a quiet stretch.
The full mapping:
A few clarifications on the rows that surprise people:
Why image build costs money. The build runs as its own workload, metered the same way as your serving replicas. Faster builds save money. Heavy or unnecessary install steps in your
config.yaml are paying for themselves on every push.
Why cold starts cost money. The replica is observed as up during model load, so those minutes are billed. See Cold starts for techniques to shrink that window.
Why failed boots are free. If the replica was never observed as up, no minutes are billed. 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 is killed mid-request. Usage is billed up to the moment the replica terminates. Partial minutes are rounded up.
Training and fine-tuning
Training and fine-tuning runs are metered the same way as serving. A run is billed for the wall-clock time between the training workload being observed as up and the job completing or being cancelled. For how training storage works, see Training storage.Instance pricing
Per-minute prices for every available instance type are listed on the instance type reference. To convert per-minute to per-hour, multiply by 60.View usage
View usage in the console, or query the same data from the Baseten CLI or the Management API to attribute costs back to teams, feed your own reporting, or alert on spend. The CLI and API return usage split into dedicated deployments, Model APIs, and training, with a per-resource breakdown and a daily series on each entry. Their window can’t exceed 31 days and can’t start before 2026-01-01 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.