Pay-as-you-go, token limits, and upgrades
Understand what happens when your org's tokens run out and our pay-as-you-go token billing
How does pay-as-you-go work, what does it cost, and when is it billed?
After your organization uses all its monthly allocated tokens, pay-as-you-go lets you keep using tokens beyond the included amount at your plan's per-1,000-token rate:
- Tree: $3 per 1,000 tokens
- Grove: $2 per 1,000 tokens
- Forest (Enterprise): customized
Pay-as-you-go usage is totaled over the billing month and billed on your next billing date (the same day your subscription renews). Sapling does not support pay-as-you-go: to get more tokens, upgrade to Tree or above.
What is a token limit?
A token limit is a monthly cap you set on how many tokens your organization can consume in a billing month, including any pay-as-you-go overage. It is the simplest way to control spend: set it to your included monthly pool to prevent pay-as-you-go charges, or set it higher to let ingestion continue beyond the pool while still capping the maximum bill. If you hit the limit, Processed Data ingestion may pause until tokens reset or the limit is increased.
When should I use pay-as-you-go instead of upgrading my plan?
Use pay-as-you-go when token needs are temporary or spiky: an initial historical ingest, a one-off project, or an occasional heavy month. Upgrade your plan when higher usage is the new normal. If you exceed your included tokens most months (for example, 3+ months in a row), a higher tier is usually more predictable than ongoing overage.
What happens if we hit our token limit?
Viewing never breaks; acting needs tokens. When you hit your monthly limit:
- Native Data syncing and Search keep working normally, they never consume tokens.
- The Loops dashboard, loop detail, citations, unified search, and calendar view stay accessible. They read from the existing graph and don't require new token spend.
- Chat (every model) pauses until your tokens reset, you increase your token limit (allowing pay-as-you-go), or you upgrade your plan.
- Processed Data ingestion pauses. Anything already ingested stays searchable; only new ingestion is affected.
- Astell Actions pause. The Agent or chat can still propose what it would do, but the action isn't pushed until you have budget.
Notifications fire at 75%, 90%, and 100% of your limit.
Related Articles
Continue learning with these related help articles