DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV
All guides
TutorialLevel · Build#Cost#Caching#Production

Prompt caching, properly measured: prefixes, writes, reads and real cost

A worked cost example, current GPT-6 cache behavior and a debugging checklist for stable prefixes, cache boundaries and reuse.

DCDariusz Czechowicz23 Sept 20263 min readPractical guide
47
Tutorial
Source-checked Sources & corrections
2 practical sections · checklist · sources

Practical guide. Provider claims are attributed to the sources below. This page does not claim a new independent DARC benchmark.

For: Developers and teams putting AI into practical use

⚡ TL;DR — the 30-second version

  • Account for writes, reads, uncached input and output separately.
  • Use current prices and workload-specific reuse.
  • A stable cache must not override data freshness requirements.

Separate stable context from per-request state. A reusable prefix might include instructions, tool definitions and reference material; user questions and changing business state usually belong after it. Confirm each provider's actual cache key and retention semantics before relying on this pattern.

Current prices illustrate why the details matter: Opus 5.5 lists $0.20 per million cache-read tokens versus $4 for uncached input. GPT-6 Sol lists $0.20 cached input versus $2 uncached input, and cache writes have their own rate. DeepSeek has both cache-hit pricing and a peak/off-peak schedule. These are billing units, not measured savings percentages.

“Cache hit rate is only half the story. A cache is useful when its writes, reads and expiry pattern reduce your real invoice.”
— Editorial interpretation

Estimate the bill from separate token buckets: uncached input, writes, reads and output. Then compare the estimate with your usage record. Include tools, long-context multipliers and any storage or service-tier costs. Cache reuse should also be tested against the application's freshness policy.

OpenAI's September changelog introduces Prompt Cache Diagnostics and documents its cache dashboard. Use actual miss reasons instead of assuming every miss is a prompt-ordering problem. Treat a lower input bill as one component of the full workload cost, not a reason to stop measuring output quality.

Field guide / 01

A worked cache example, with the denominator visible

Suppose a reusable prefix is 10,000 tokens, its ordinary input rate is $2/M, its write multiplier is 1.25 and its read multiplier is 0.10. Across ten requests with one write and nine complete hits, the prefix costs $0.043 rather than $0.20 uncached. This is arithmetic under stated assumptions, not a measured saving for an application.

The changing suffix, outputs, tools and retries still cost money. If the prefix changes or expires, another write changes the result. Use the same accounting for a cold request, a warm request and a request after compaction.

formula
input_cost = (ordinary_tokens × ordinary_rate
            + write_tokens × write_rate
            + read_tokens × read_rate) / 1,000,000

Each input token belongs to one billing bucket, not all three.
Unit prices are per million tokens. Avoid double-counting writes as ordinary input plus an additive write fee.

Field guide / 02

GPT-6 caching is not the older retention interface

The current OpenAI guide documents prompt_cache_options, explicit breakpoints and a 30m TTL for GPT-5.6 and later. It distinguishes those models from earlier prompt_cache_retention behavior. Read the current compatibility table before copying a caching recipe written for an older model.

Measure cache-write and cached-token fields and inspect diagnostics for misses. Preserving a logical conversation does not guarantee an identical rendered prefix; tool ordering, schemas and configuration can change it.

Before you ship

0/5

Use this as a review aid. Checks reset when you leave this page.

Questions that come up

Does a cache return the same answer?

No. Prompt caching reuses prefix computation. The model still generates a new response; it is not a response cache.

Put it into practiceExplore cache economics in the Lab

Sources & verification

Last checked 23 Sept 2026. Publication dates and access conditions belong to the linked originals.

  1. 01Introducing Claude Opus 5.5Anthropic↗
  2. 02GPT-6 Sol API model and pricingOpenAI↗
  3. 03DeepSeek models and pricingDeepSeek↗
  4. 04OpenAI API changelogOpenAI↗
  5. 05OpenAI — current prompt-caching behaviorOpenAI↗
  6. 06OpenAI — model migration and cache changesOpenAI↗
Editorial policy and correction log →
#Cost#Caching#Production