Posts tagged prompt-cache

13 posts about prompt-cache.

• Prompt Cache Minimums: The Docs Under-State by 1.4–2.4x

  July 12, 2026 · prompt-cache · llm-cost · evaluation

  Vendors publish a prompt-cache token minimum. Measured across LLM families, auto-cache needs 1.4–2.4x more than the docs say; Claude's explicit cache is exact.

• GPT-5.6 Cost Guide: Prompt Caching 90% Off, Reasoning Effort

  July 10, 2026 · gpt-5.6 · prompt-cache · reasoning · cost

  GPT-5.6's two cost levers, measured: explicit breakpoints bill cached input at 10% of the rate, and not sending reasoning_effort bills 1.5x as much as none.

• LangChain Prompt Caching: Setups That Actually Hit the Cache

  July 4, 2026 · prompt-cache · langchain · tutorial

  LangChain's friendliest syntax silently disables Claude's prompt cache. Measured fixes: cache_control via content blocks, variable placement, usage fields.

• Claude Sonnet 5's New Tokenizer: 41% More Tokens per Prompt

  July 1, 2026 · claude-sonnet-5 · prompt-cache · cost · model-update

  Claude Sonnet 5's new tokenizer makes the same text about 41% more tokens than Sonnet 4.6, reshaping cost, budgets, and cache eligibility on the gateway.

• Open-Weight LLM Caching: Why Yours Is Provider Roulette

  June 14, 2026 · prompt-cache · open-weight-llm · inference · deepseek

  For open-weight LLMs, prompt caching is solved in the inference engine and broken by routing. A five-layer map, measured across DeepSeek, Qwen and Kimi.

• Claude Fable 5 Caching: Same Contract, 2.9x the Bill vs Opus 4.6

  June 10, 2026 · claude-fable-5 · prompt-cache · tokenizer · model-update

  Claude Fable 5 is live on Synthorai. Measured prompt caching, TTL, tokenization and cost vs Opus 4.6/4.8: same cache contract, new tokenizer, ~2.9x the bill.

• Provider Drift: How Default Routing Inflates LLM Cost

  June 5, 2026 · prompt-cache · llm-gateway · routing

  On a multi-provider gateway's default routing, identical requests scatter across upstreams with separate caches. Hit rate craters and your bill climbs.

• Does Your LLM Gateway Lie About Cache? A 5-Min Audit

  June 2, 2026 · llm-gateway · prompt-cache · observability

  Gateways can report cache hits while billing full price. One script audits both auto-cache (DeepSeek) and marker-based (Claude) caching in five minutes.

• Claude Opus 4.8 on Synthorai: Caching & TTL vs 4.7/4.6

  May 29, 2026 · claude-opus-4-8 · prompt-cache · model-update

  Claude Opus 4.8 is live on Synthorai. Measured prompt caching and TTL behavior vs Opus 4.7/4.6 — what carries over, plus the tokenizer shift to re-check.

• LLM Prompt Caching: The Complete 2026 Guide

  May 26, 2026 · prompt-cache · series-overview · llm-architecture

  A five-part series on LLM prompt caching: KV cache architecture, provider comparison, Python tutorial, model-by-use-case matrix, LangChain integration.

• LLM Prompt Caching in Python: A Working Code Tutorial

  May 24, 2026 · prompt-cache · tutorial · python

  Measured prompt-cache savings across Claude, GPT-5, Gemini 2.5, DeepSeek-v4 and Qwen3 via Synthorai's OpenAI-compatible gateway. Real usage.cost and TTFT.

• Prompt Caching Compared: Claude, GPT-5, Gemini, DeepSeek, Qwen (2026)

  May 23, 2026 · prompt-cache · llm-providers · evaluation

  Anthropic Claude, OpenAI GPT-5, Gemini 2.5, DeepSeek-v4 and Qwen3 expose prompt caching in five different shapes — measured 2026 feature comparison.

• How LLM Prompt Caching Works: KV Cache & TTL Explained

  May 22, 2026 · prompt-cache · transformer · llm-architecture

  How LLM prompt caching actually works: Transformer attention math behind K/V reuse, the memory-compute tradeoff that shapes TTL, and why it cuts cost and TTFT.