Skip to main content
Charged tokens are the units deducted from a Capriole AI API balance. Personal Premium includes 5 million per month as part of the USD 9 workspace membership. Uncached input and output count at 100%. Cached input counts at 10%, rounded up to the next whole token. They apply to public API and coding-agent traffic, which costs up to 92% less than official API prices. Unlimited Premium browser chat does not consume this API balance.

The formula

Capriole normalizes each supported protocol into a total input-token count and, when the selected provider reports it, a cached-input count. Cached input is a subset of total input.
If the provider reports no cached input, all input tokens count at 100%. For Anthropic Messages, cache creation remains 100% input. Only reported cache reads receive the 10% charged-token treatment.

Three reproducible examples

The third request has 228,897 raw input-plus-output tokens. It deducts 23,496 charged tokens because the provider reported 228,224 input tokens as cached. Rounding happens on the cached portion of each recorded request. One cached input token therefore charges one token after ceil(0.1), while ten cached input tokens also charge one token.

Estimate how many requests fit in 5 million charged tokens

Use the average charged-token value from your own API usage instead of guessing from raw context size.
These rows are planning arithmetic, not typical workload claims. A short classification call and a long coding-agent turn can differ by orders of magnitude. Output length, repeated context, provider-reported cache hits, and tool results all change the measured average.

Charged tokens and provider prices use different units

Official providers may publish separate prices for input, cached input, cache writes, output, tools, or long contexts. Capriole’s charged-token balance is a customer quota unit with one formula across supported public API routes. Do not multiply charged tokens by a provider’s published input or output rate. The units describe different billing systems. The dated API cost comparison applies this formula to one fixed 5 million-token workload and then compares the cash cost under each service. Claude API pricing, OpenAI API pricing, and Gemini API pricing compare the current official rates per 1M tokens with Capriole’s USD 8 per 5M tokens.

Personal and Team balance boundaries

Included quota is consumed before the matching personal or Team top-up wallet. Purchased top-up balances persist across monthly quota periods and paid-access gaps; consuming them still requires eligible active paid access. Browser chat is separate from API accounting; coding agents count as API traffic and deduct charged tokens. The USD 9 Premium subscription includes 5 million charged API tokens each month.

What the API records

Capriole keeps protocol-normalized usage and charged usage as separate fields. A successful public API request can record:
  • normalized input tokens;
  • output tokens;
  • normalized input-plus-output tokens;
  • provider-reported cached input tokens;
  • charged tokens deducted from quota;
  • the resolved model and request status.
The Responses, Chat Completions, and Messages endpoints keep their upstream response shapes and do not return a charged_tokens field. Capriole records the matching charged-token value for account usage; you can see it in the Charged tokens column of the usage table on the API page.

Confirm whether cached input reduced a charge

Open the Capriole AI API page, then use the Key, Model, and Status filters to isolate the request. Compare these columns in the usage table: A positive cached-token value confirms that compatible provider usage metadata reported a cache hit. Provider routing, cache lifetime, request structure, and model behavior can change the result. API responses keep their upstream schemas, so the account usage table is the consistent place to compare requests across routes.

Common questions

Does cached input always receive the 90% quota discount?

The 90% discount applies to cached input tokens identified in the provider’s usage metadata. Other input tokens count at the standard rate.

Are reasoning tokens added a second time?

No. Provider-reported output usage already contains the output accounting used by the route. Capriole does not add a separate reasoning-token charge on top of output for this formula.

How does Premium bill API and coding-agent requests?

Premium includes 5M API tokens a month for apps and coding agents. Top-ups cost USD 8 per 5M tokens.

Where should I start coding?

Use the API quickstart for the smallest raw request or the OpenAI and Anthropic SDK guide for protocol-native Python and TypeScript clients. If you have not subscribed yet, try the flagship models in free browser chat before upgrading. Capriole plan, quota, top-up, and charged-token facts on this page are maintained as first-party documentation.
Last modified on November 18, 2026