Skip to content

Limits & quotas

A reference of the operational limits that apply to your workspace.

Monthly token budget

TierBudgetBehaviour at cap
Starter20,000,000 tokensTelegram alert at 80%. Default overage policy: alert (notify, do not block).
Growth40,000,000 tokensTelegram alert at 80%. Default overage policy: alert (notify, do not block).
EnterpriseUnlimitedNo monthly cap.

See token meter.

Per-tool limits

ToolLimit
execute_code15-second timeout per execution.
Tool output payloadCapped at ~50,000 characters per call.
page_fetchReturned page text capped at ~20,000 characters.
Telegram messageTelegram’s 4,096-character limit applies. Longer outputs are split or delivered as a PDF.
Voice noteTranscribed by local whisper.cpp where installed, with OpenAI Whisper API fallback.
Vector memoryBounded by your VPS disk allocation.

Concurrency

Han AI handles one conversation turn at a time per workspace. Scheduled jobs run on cron and do not block your live conversation.

Storage

Operational state on your VPS is bounded only by your VPS disk allocation. Backups follow the DPA retention defaults — 30 days rolling.

See also