Billing

Charging is by actually used tokens, separately for input and output, at the model's rate. The balance is on the dashboard and in the bot.

The table above is built from the gateway billing catalog, so the numbers are never retyped into the documentation text and never drift from what the charge is computed on. The key keeps one balance for every family.

The part of the input Kimi recognized from its own cache is charged at the separate Cache read rate. For k3 and k3-256k it is ten times below the input rate; for kimi-for-coding and kimi-for-coding-highspeed it is five times below. Nothing is paid twice: cached tokens are subtracted from the ordinary input. How many there were is visible in the response — usage.prompt_tokens_details.cached_tokens. Kimi does not bill cache writes separately.

Before calling the model, Guard reserves estimated input cost plus the maximum output cost. For Kimi without max_tokens, 32,000 output tokens are used. A confirmed 25% PRIVATE discount is included in the reserve; a future cache hit is not assumed. Unused reserve is released.

Before the model is called, Guard temporarily holds the largest possible cost of the request. The input part is estimated from above: the UTF-8 bytes of the request itself — the system text, the messages and the tool descriptions. That is deliberately more than the real token count, but it never under-holds on code, JSON or non-Latin text. The output part follows max_tokens, or max_output_tokens on the Responses surface; when no limit is set, 32,000 is used. A confirmed 25% PRIVATE discount is included in the reserve.

Claude without an actually applied server prompt receives 25% off. With an applied prompt, the base rate applies. Confirmed PRIVATE members receive 25% off all four families, with or without a prompt. Eligibility conditions do not stack. The discount applies after caching; historical financial records are not recalculated. Full conditions.

Web search adds $0.01 per metered billed search request. This fixed fee is not reduced by 25%, including for PRIVATE. Web fetch has a $0 fixed fee. Retrieved content is accounted as input tokens under the usual cache and discount rules.

Each key can have its own USD cap for a rolling hour and/or 24 hours: @subscribe_ai_bot → My API keys → choose a key → Manage API key → limits. Set 0 or use the clear action to remove limits.