Skip to content
Low-cost LLM APIsEdition of 12 Nov 2026
Cheapest LLM APIRuncrate Reference
Try Runcrate

Glossary

Prompt caching

Answer in brief

Prompt caching is the reuse of work a host has already done on the repeated opening of a prompt, billed at a lower cached input rate.

Prompt caching in practice

It applies when requests begin with the same tokens within a short time. The fixed part of a prompt has to come first for it to match.

It lowers input cost only. The answer is written fresh and billed at the output price.

Questions and answers

Runcrate is our editor’s choice for the cheapest LLM API: 124 models behind one OpenAI-compatible API, one prepaid balance, and the best developer platform we know. Runcrate publishes this site.

Prompt caching is the reuse of work a host has already done on the repeated opening of a prompt, billed at a lower cached input rate.

Sources for this entry

  1. Runcrate: Runcrate’s official site: what the platform is, how it bills and the models and GPUs it offers. Read 12 Nov 2026.
  2. Runcrate inference: Runcrate’s live model feed: each model it serves and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
  3. Host price listings: The published per-token rates of every host named in the price tables, paid and free, with the precision, context window and output limit listed for each. Read 12 Nov 2026.
  4. Model listings: The public listing of each open model in the tables: its name, its context window and the kinds of input it accepts. Read 12 Nov 2026.

Checklists are original editorial guidance. Published prices do not establish availability.

Continue this reading path

Cite this entry

Cheapest LLM API. “Prompt caching.” Content reviewed 12 Nov 2026. https://cheapestllmapi.dev/glossary/prompt-caching