# The AI costs that accrue when you make no calls at all > A held Gemini cache costs $144 a month at zero calls. An always-on 64 GB container costs $4,147.20. Call-based tools can't see either. URL: https://getculpa.com/idle-llm-cost Last reviewed: 2026-08-05 Rates effective: 2026-07-02 ## Answer Some provider charges bill by elapsed time rather than per request, so they accrue while your product sits idle. Held caches, running containers and agent sessions all cost money at zero calls. Culpa, a local-first LLM cost, margin, and forecast ledger, prices calls exactly, and these belong to a different shape worth measuring separately. ## Why this happens Almost everything written about AI cost assumes cost follows usage, and for tokens it does. Three charges break that assumption by billing on elapsed time. A context cache bills for the tokens it holds, every hour it holds them, whether you read it once or never. A container or code-execution sandbox bills for as long as it's alive. An agent session bills for its running time. None of them produce a request, so none of them appear in anything that counts requests, and they're invisible to any tool built on a log of calls. The reason this bites rather than merely annoys is that the cheapest way to make something fast is usually to leave it warm, and warm is exactly what these charges price. A cache with a generous lifetime and a container left running are both rational engineering decisions that quietly convert latency into rent. ## What this usually looks like - Your invoice has line items that aren't token charges and nobody owns them. - Spend doesn't fall as much as expected during a quiet week. - A container or sandbox has been running longer than anyone remembers. - Cache lifetimes were set once and never revisited. - Your cost tooling reconciles on calls and still comes in under the invoice. ## Common mistakes - Assuming cost follows usage. Why it hurts: Time-based charges accrue at zero usage, so a quiet period costs more than it looks like it should. Do instead: Separate charges that follow requests from charges that follow the clock. - Setting a generous cache lifetime for safety. Why it hurts: Storage bills for hours held, so an over-long lifetime is rent on context nobody read. Do instead: Set the lifetime from how long you actually reuse the context, then check it against reality. - Leaving containers warm to avoid cold starts. Why it hurts: It's a real latency win and a standing charge, and only one of the two is usually measured. Do instead: Price the warm hours and decide deliberately, rather than defaulting to always-on. - Sizing a container generously because it's cheap. Why it hurts: Size and time multiply, so the largest tier costs many times the smallest for identical hours. Do instead: Size to the job, and revisit it once you've seen real memory use. ## Self-check - Find the non-token line items on last month's provider invoice and total them. - List every cache, container and session you hold, and how long each one lives. - Work out what a quiet weekend costs you before a single call is made. - Check whether any resource has been running longer than the work that needed it. ## What a quiet month costs at zero calls (illustrative) Published rates read 2026-08-05. Gemini charges context cache storage at $1.00 per 1,000,000 tokens per hour on most models, rising to $8.10 on 2.5 Pro Priority. OpenAI charges container sessions at $1.92 per 20-minute session for the 64 GB tier. Anthropic charges code execution at $0.05 per hour per container with 1,550 free hours per organisation per month. The holdings below are modelled, every rate is published. a 200,000-token Gemini cache: 0.2M x $1.00 x 24 x 30 = $144.00 a month the same cache on 2.5 Pro Priority: 0.2M x $8.10 x 24 x 30 = $1,166.40 a month a 64 GB OpenAI container: $1.92 per 20 minutes = $5.76 an hour left running: $5.76 x 24 x 30 = $4,147.20 a month Anthropic code execution stays free below 1,550 hours, which is about 18,600 five-minute sessions Every figure above is what you pay having made no requests at all. The Anthropic number is the encouraging one and it's worth stating plainly, because a free allowance that generous means most teams owe nothing there. The Gemini and OpenAI numbers are the ones to go and check tonight. ## Cost figures Every figure carries its confidence and its source. No figure on this page is provider-reported. - $144.00 per month, modelled cost of holding a 200,000-token Gemini context cache, making no calls [calculated] Source: Gemini's pricing page, read 2026-08-05, publishes context caching storage at $1.00 per 1,000,000 tokens per hour on most models. 0.2M tokens x $1.00 x 24 hours x 30 days = $144.00. On the 2.5 Pro Priority rate of $8.10 the same holding is $1,166.40. The rates are published, the cache size and the holding period are modelled. - $4,147.20 per month, modelled cost of one always-on 64 GB OpenAI container, making no calls [calculated] Source: OpenAI's pricing page, read 2026-08-05, publishes container sessions at $1.92 per 20-minute session for the 64 GB tier, billed by the minute with a five-minute minimum, so $5.76 an hour, so $5.76 x 24 x 30 = $4,147.20. The rate and the tier are published, the always-on assumption is modelled. ## FAQ Q: Can an LLM cost money when nobody is using it? A: Yes. A held Gemini context cache bills for the tokens it stores every hour it stores them, so a 200,000-token cache costs $144.00 a month at the standard rate with zero calls. Running containers and agent sessions bill the same way, on elapsed time rather than requests. Q: Why doesn't my cost tool show these charges? A: Because they produce no request. Cost tooling almost universally works from a log of calls, and a cache sitting idle or a container sitting warm generates no call to log. It isn't a capture bug so much as a shape the call-based model has no room for. Q: How do I find my exposure? A: Open your provider console and look at the line items that aren't token charges. Gemini itemises caching storage, OpenAI itemises container and training charges, Anthropic itemises code execution. Compare that total against the gap between your invoice and whatever your cost tooling reports. Q: Is keeping a cache warm still worth it? A: Often yes, and it's a trade rather than a mistake. Cache reads cost a fraction of fresh input tokens, so a cache read enough times pays for its storage several times over. The failure mode is a long lifetime on context nobody reads, which is rent with no return. Price the hours against the reads. ## Sources - Gemini API pricing: https://ai.google.dev/gemini-api/docs/pricing - OpenAI API pricing: https://developers.openai.com/api/docs/pricing - Anthropic pricing: https://platform.claude.com/docs/en/docs/about-claude/pricing Run the free Cost Leak Scan: https://app.getculpa.com/scan?source=pseo&slug=idle-llm-cost&cluster=problem Machine-readable index of every guide: https://getculpa.com/api/pages Human-readable index of every guide: https://getculpa.com/guides Site overview: https://app.getculpa.com/llms.txt Privacy: Culpa runs on your infrastructure. Your prompts and responses never leave it. Culpa counts calls to run your plan, and it fails open, so if it ever breaks your app keeps running.