Go back

What are tokens?

A quick introduction to how tokens work when using Astell

What are tokens?

Tokens measure usage for Processed Data ingestion (documents, images, audio, video, meetings, and web pages). Most of Astell (like Standard chat and Native Data syncing) is unlimited and free. Advanced models don't consume tokens—they're limited by a separate Advanced response allowance that resets on your billing cycle. Starting on Tree, tokens are pooled at the organization level, meaning your org's monthly token total is (tokens per seat) × (number of seats). Customized admin control for token consumption is available on Grove and Forest. If you exceed your included tokens, usage continues on pay-as-you-go at your plan's per-1,000 token rate, and you can set a token limit to control spending. Overage is billed at the beginning of your next billing month.

Which features don't consume tokens?

These features are unlimited and always available (only subject to the Fair Use Policy):

• Standard AI chat models
• Native Data syncing (messages, emails, tasks, code)
• Searches across your data
• Team collaboration features
  Please check out our Fair Use Policy

Which features consume tokens, and what are the token rates?

• Image ingestion: 1 token/image
• Audio ingestion: 2 tokens/minute
• Document ingestion: 5 tokens/page
• Web page ingestion: 5 tokens/page
• Meeting ingestion: 8 tokens/minute
• Video ingestion: 8 tokens/minute

What token allocation is included in each plan?

• Sapling Plan
  • 2,500 tokens/seat/month
  • Best for: Solo users who want to find the right info fast and get through daily work with less digging.
  • Approx: 500 document pages
• Tree Plan
  • 10,000 tokens/seat/month
  • Best for: Teams who need shared answers, smoother handoffs, and support for files and richer media. It can also consolidate tools by covering web search and deeper research needs in one workspace.
  • Approx: 2,000 document pages
• Grove Plan
  • 30,000 tokens/seat/month
  • Best for: Larger orgs with complex permissions and workflows, plus Ultra mode and much higher quotas.
  • Approx: 6,000 document pages
• Forest (Enterprise) Plan
  • Contact founders@labtwofour.com for custom pricing
  • If you want to learn more about our Enterprise offerings, see “Forest (Enterprise) Plan”.

Are tokens pooled across users or assigned per user?

On Tree and above, tokens are pooled across the organization. There is one shared token balance for the org, and all seats draw from the same pool.

How many tokens does my organization get if I have multiple seats?

Your organization's monthly tokens are calculated as (plan tokens per seat) × (number of seats). For example, an organization with 10 users on Tree receives 100,000 tokens per month (10 × 10,000).

Can one user spend all of an organization's pooled tokens?

Yes. Since tokens are pooled, any user activity that ingests Processed Data draws from the shared balance. If you need granular controls over who can use tokens and how, use Grove or Forest, which support customized permission structures.

What is a token limit, and how does it control pay-as-you-go spend?

A token limit is a monthly cap you set on how many tokens your organization is allowed to consume in a billing month, including any pay-as-you-go overage. It helps prevent unexpected charges. If you hit the token limit, Processed Data ingestion may pause until the next reset or until the limit is increased.

What happens when my organization is running out of tokens?

When your organization approaches its monthly token allocation, you can either allow ingestion to continue on pay-as-you-go, or set a token limit to prevent additional billed usage. If ingestion hits your token limit, Processed Data ingestion may slow down or pause until tokens reset on your billing cycle.