{"slug": "claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved", "title": "Claude vs GPT-5.6 vs Gemini vs DeepSeek Prompt Caching: I Turned It Off and Saved 20%", "summary": "A developer who turned off prompt caching on a Claude Opus 5 assistant saw input costs drop 20%, from $4.61 to $3.69 for 41 requests over 8 hours, because cache writes are now billed at a 1.25x premium with a 5-minute TTL on Anthropic and a 30-minute TTL on OpenAI's GPT-5.6, making caching a net loss when cache entries expire before reuse. The developer created a 200-line script to price caching across Claude, GPT-5.6, Gemini, and DeepSeek, finding that caching can act as a 25% surcharge rather than a 90% discount.", "body_md": "Member-only story\n\n# Claude vs GPT-5.6 vs Gemini vs DeepSeek Prompt Caching: I Turned It Off and Saved 20%\n\nI turned prompt caching **off** on a Claude Opus 5 assistant last week and the input bill dropped 20% — from $4.61 to $3.69 for the same 41 requests over the same 8 hours.\n\nThat is not how caching is supposed to work. Every provider doc leads with the same number: cached reads cost 90% less than fresh reads. A 10x discount. Free money for anyone with a stable system prompt.\n\nThe catch is that since **July 9, 2026**, when GPT-5.6 went GA across Sol, Terra and Luna, cache *writes* are billed on both of the two biggest APIs. OpenAI replaced its old free implicit writes with explicit breakpoints, a 1.25x write premium and a 30-minute TTL, which lands it almost exactly where Anthropic has been all along. Prompt caching stopped being a one-way bet and became a wager: you pay a premium up front for a discount you might never collect.\n\nIf your cache entry expires before anyone reads it, you paid the premium for nothing. My assistant had 12 minutes between turns and Claude’s default TTL is 5 minutes. Every single request was a cold write at 1.25x. Caching was a 25% surcharge dressed up as a 90% discount.\n\nI wrote a 200-line zero-dependency script to price out all four providers properly. Three findings I did not expect:", "url": "https://wpnews.pro/news/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved", "canonical_source": "https://pub.towardsai.net/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved-20-2eb63761becd?source=rss----98111c9905da---4", "published_at": "2026-07-30 10:16:08+00:00", "updated_at": "2026-07-30 10:40:38.589620+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "developer-tools"], "entities": ["Claude Opus 5", "GPT-5.6", "Gemini", "DeepSeek", "Anthropic", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved", "markdown": "https://wpnews.pro/news/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved.md", "text": "https://wpnews.pro/news/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved.txt", "jsonld": "https://wpnews.pro/news/claude-vs-gpt-5-6-vs-gemini-vs-deepseek-prompt-caching-i-turned-it-off-and-saved.jsonld"}}