AI services have their own resource use.

You would pay for

• ›Input, cached-input and output tokens, per model
• ›Usage drawn from prepaid credit, with the balance as the spending cap

The supported model catalog and rates will be published at launch.

Source: planning record, as of 2026-09-24.

You would pay for

• ›Memory tokens (extraction and embeddings)
• ›Retained memory storage, per GB-month
• ›Not metered: retrievals, agents, end users or seats

Rates not yet published.The API shape, retention controls and bring-your-own-key options are still being decided.

Source: planning record, as of 2026-09-24.

You would pay for

• ›Stored GB-month
• ›Writes and reads
• ›Not billed: egress, links, viewers or seats

Rates not yet published.Planned as a convenience inside our agents, not a standalone storage product.

Source: planning record, as of 2026-09-24.

Cost drivers

• ›Persistent compute, disk and network
• ›Tool sandbox time
• ›Model consumption and backups

Rates not yet published.Idle suspension, GPUs and support for every channel are not promised.

Source: planning record, as of 2026-10-04.