Skip to main content
Paid plans include their monthly price in usage; Free includes a small amount. Calls are charged at your plan’s rates per input token, output token and search.

​
Plans

Every plan includes all decision kinds, images, grounding and reasoning. Your plan and rates: Billing page. Enterprise volume: team@levanto.ai.

​
What counts

  • Input tokens: everything Sage reads, including images. Sage reads the content once per question, once per tag in Tags, and once per item in Sort.
  • Output tokens: one per answer, plus thinking when Sage reasons.
  • Searches: each grounding search that runs.
meta.usage on every response reports input_tokens, output_tokens and image_tokens. To count before sending, post the same body to POST /usage/estimate. It returns a range when reasoning or search may run; images are not included. Unused usage doesn’t roll over. When it runs out, calls return 402 until the next period or an upgrade. No seats, no overage invoices.

​
Spend less

  • Send only the content a question needs.
  • One Choice question often replaces several Yes/No questions.
  • Leave reasoning off unless a question needs it.