{"type":"analysis","id":"analysis:guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how","slug":"guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how","title":"Prompt caching at Anthropic, OpenAI and Google: how it is billed and how to hit the cache","description":"Prompt caching reuses a stable prompt prefix so later requests pay a discounted cache-read rate instead of full input. Anthropic is opt-in via cachecontrol (automatic top-level or up to 4 explicit block breakpoints); default TTL 5 minutes (optional 1h); writes cost 1.25x/2x base input and reads usua","published_at":"2026-11-12T09:00:00.000Z","updated_at":"2026-11-12T09:00:00.000Z","record_date":"2026-11-12","topics":["tools","developer_tools"],"source_urls":["https://docs.claude.com/en/docs/build-with-claude/prompt-caching","https://developers.openai.com/api/docs/guides/prompt-caching","https://ai.google.dev/gemini-api/docs/caching","https://aistudio.google.com/api-reference/caching.md","https://platform.claude.com/docs/en/about-claude/pricing","https://ai.google.dev/gemini-api/docs/pricing","https://docs.cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview","https://openrouter.ai/docs/guides/best-practices/prompt-caching","https://developers.openai.com/api/docs/pricing"],"language":"en","routes":{"html":"https://newruntime.com/analysis/guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how/","markdown":"https://newruntime.com/analysis/guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how.md","json":"https://newruntime.com/analysis/guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"practical:de5293a4-2043-45d0-a8b9-77e25439c3fd","authorial_article_id":null},"markdown_url":"https://newruntime.com/analysis/guide-prompt-caching-at-anthropic-openai-and-google-how-it-is-billed-and-how.md","retrieval_nugget":"Prompt caching reuses a stable prompt prefix so later requests pay a discounted cache-read rate instead of full input. Anthropic is opt-in via cachecontrol (automatic top-level or up to 4 explicit block breakpoints); default TTL 5 minutes (optional 1h); writes cost 1.25x/2x base input and reads usua","next_reads":[{"type":"topic","path":"/topics/tools/","url":"https://newruntime.com/topics/tools/","title":"Tools","reason":"Explore the tools topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/tools.md","json_url":"https://newruntime.com/topics/tools.json"},{"type":"topic","path":"/topics/developer-tools/","url":"https://newruntime.com/topics/developer-tools/","title":"Developer Tools","reason":"Explore the developer_tools topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/developer-tools.md","json_url":"https://newruntime.com/topics/developer-tools.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}
