If you ship a chatbot, a RAG app, or an AI agent against a large language model, prompt caching is the single optimization that gives you back 50–90% of input cost and 3–10× of time-to-first-token at no quality cost. It isn't a bolt-on trick — it falls directly out of how Transformer attention is defined. Once you understand that, the rest of the stack (TTLs, provider differences, prompt structure) lines up cleanly. This page is the index to a four-part series that takes you from the theory to a production decision matrix. Pick where to enter based on what you already know.
| If you want to... | Start at |
|---|---|
| Understand why caching exists and what KV cache actually is | |
Each part stands alone but they're written so reading them in order builds the picture without redundancy.
LLM Prompt Caching #1: How KV Cache & TTL Work →
The architectural article. Walks through self-attention as a single equation, explains why the K and V vectors of a stable prefix are mathematically reusable, and shows how the memory-vs-compute tradeoff produces the TTL behavior every developer has to design around.
Key takeaways:
i
is a deterministic function of tokens 1…i
, so identical prefixes give bit-identical K/V.LLM Prompt Caching #2: Compare Claude, GPT, Gemini, DeepSeek →
The buyer's guide. Five providers expose prompt caching in five very different shapes — explicit markers (Claude), fully automatic (GPT-5, DeepSeek-v4), hybrid implicit+explicit (Gemini, Qwen), or architectural disk-backing (DeepSeek's MLA). The article gives a feature-by-feature comparison plus a 5-dimension evaluation framework to score them for your specific workload.
Key takeaways:
cache_control
markers.LLM Prompt Caching #3: Working Python Tutorial →
The hands-on article. One OpenAI SDK + one Anthropic SDK against a single gateway, with measured numbers from 2026-05-25 across the full Claude family (haiku-4-5 through opus-4-7), GPT-5.x, Gemini 2.5, DeepSeek-v4, and Qwen3.
Key takeaways:
cache_control
markersbase_url="https://synthorai.io/"
.LLM Prompt Caching #4: Best Model for Chat, RAG & Agents →
The decision article. Different workloads pull the cost/latency levers differently — chat is naturally cache-friendly, RAG fights the prefix-stability problem, agents depend on cumulative prefix discipline. The article gives a model recommendation by workload shape with cost estimates.
Key takeaways:
`gpt-5.4-nano`
cheapest, `gpt-5.4-mini`
fastest cached TTFT, `claude-haiku-4-5`
best instruction-following at modest premium.cache_control
breakpoints.claude-sonnet-4-5
with 4 cache_control
markers gives the strongest cumulative-prefix discount; gpt-5.4-mini
works without code changes at 50% savings.All measured numbers were captured on 2026-05-25 against the Synthorai gateway (https://synthorai.io/v1
for OpenAI-compat, `https://synthorai.io/`
for Anthropic-native), single-tenant, single sequential run, no concurrent load. Your numbers will move with region, time-of-day, and competing tenant load — treat them as a starting point and reproduce against your own traffic before quoting them.
Pricing tables and TTL behavior reflect vendor public documentation as of 2026-05. Providers update these every few months; the architectural reasoning (Part 1) is stable, the comparative numbers (Part 2 & 3) drift.