# Cache tokens

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: cached tokens, cache read tokens, cache hits, cached input, cache hit tokens

[Input tokens](https://ecosystem.samcarlton.com/input-tokens) the provider did not need to process again because they matched the start of a recent request in its [cache](https://ecosystem.samcarlton.com/cdn). They appear as their own line on usage reports and cost much less than ordinary input tokens.

**For example:** A [founder](https://ecosystem.samcarlton.com/founder) opens the usage [dashboard](https://ecosystem.samcarlton.com/dashboard) and sees that most of the [agent](https://ecosystem.samcarlton.com/ai-agent)'s input was cache tokens, which explains why the bill was lower than expected.

## Connects to (6)

- [Prefix cache](https://ecosystem.samcarlton.com/prefix-cache): A provider feature that remembers the opening of a request it has just handled.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Model provider](https://ecosystem.samcarlton.com/model-provider): The company or service that runs an AI model and answers requests to it, usually over the internet through an API.
- [Usage-based pricing](https://ecosystem.samcarlton.com/usage-based-pricing): A way to charge where the bill follows how much the customer uses, instead of a flat fee.
- [Startup ecosystem](https://ecosystem.samcarlton.com/startup-ecosystem): The people, money and organizations in one place that help new companies start and grow.

## Sources

- <https://platform.claude.com/docs/en/build-with-claude/prompt-caching>


Map view: https://ecosystem.samcarlton.com/cache-tokens