FAQ
Everything the tool assumes, in plain words
Counting, pricing, privacy and the parts of an invoice the calculator deliberately does not model.
FAQ
Questions people ask before trusting a number
Does TokenLedger send my prompts anywhere?
No. The estimator, the cost simulator and the subscription comparison all run as JavaScript in your tab. There is no backend that receives your text, no analytics product reading it, and no storage: close the tab and the prompt is gone. The only file the page fetches is OpenAI's public o200k_base vocabulary, and only after you start typing, so that exact counts can be computed offline on your machine. Your prompt text is never part of that request.
How accurate is the token estimate?
For OpenAI models the page can count exactly: once the o200k_base vocabulary has loaded, every OpenAI figure is a real byte-pair count, not a guess. The fast estimate used before that, and for Claude and Gemini, is a calibrated model: across 286 mixed samples of prose, HTML, JavaScript, CSS, JSON, Korean, Chinese and Japanese text it stayed within 4.6% of the real o200k count on average, and within 9.8% for nine samples out of ten. Very short strings (a word or two) can be off by a token, which matters more in percentage terms than in money. Dense JSON, long numbers and CJK text are the weak spots: 11–19% at the 90th percentile in our samples.
Why are Claude and Gemini counts marked with a ≈?
Anthropic and Google do not publish their tokenizer vocabularies, so nobody outside those companies can reproduce their counts byte for byte in a browser. The page scales the o200k count by a family factor (+10% for Claude, +2% for Gemini) taken from how those tokenizers behave on English prose. Treat those columns as planning numbers with roughly a 10% band, and use the provider's own count endpoint when a bill depends on the last token.
Which prices are in the table?
Standard-tier, short-context, global list prices in US dollars per million tokens, as published by OpenAI, Anthropic and Google on 18 November 2026. Cache-hit rates are the published cached-input prices. Batch pricing is applied as the 50% discount each provider offers. Introductory prices are in the table as they stand today and carry a note where they step up later — Gemini 4 Carbon and Argon move from $2/$10 to $4/$20 on 1 December 2026, and Gemini 3.8 Flash from $0.75/$3.75 to $1.50/$7.50 on 1 January 2027.
How is the monthly figure calculated?
Cost per call is (uncached input × input price + cached input × cached price + output × output price), divided by one million, then halved if batch pricing is on. Monthly cost is that number × calls per day × billing days. Annual cost is twelve months at the same volume. Nothing else is added: no retries, no evaluation runs, no embedding calls, no storage or egress, no committed-use discounts, no tax.
What is a cache hit rate, and why does it change the bill so much?
Providers let you resend a long, stable prefix — a system prompt, a policy document, a codebase summary — and charge the repeated part at a cached rate instead of the full input rate. On most current models that cached rate is 5–10% of the normal input price, so a workload with a large shared prefix can cut its input cost by more than half. The slider asks what share of your input tokens are repeats; it does not model cache writes, which are billed separately (and are usually more expensive than a normal input token).
Does the batch toggle apply to every provider?
The 50% figure is what OpenAI's Batch API, Anthropic's batch processing and Gemini's batch tier all charge relative to their standard rates. If you are mixing providers or using a tier that excludes batch (some preview models do), leave it off and read the result as standard pricing.
What is not in the cost model?
Things that quietly appear on real invoices: retries and agent loops that resend the same context, reasoning tokens (billed as output), tool and function schemas (billed as input on every call), image and audio tokens, embedding calls for retrieval, vector storage, cache-write tokens, long-context multipliers above the model's short-context threshold, minimum spend, and taxes. Add a 10–30% buffer on top of any estimate that will be used for a budget rather than a comparison.
How do I get an exact count for a real request?
Ask the provider. Every API response carries a usage object (prompt tokens, completion tokens, cached tokens), and Anthropic and Google expose counting endpoints that price a request before you send it. Paste the numbers you measured into the simulator — the token fields are editable — and the comparison becomes a bill, not an estimate.
Can I add a model that is not listed?
Yes. The custom row under the model picker takes a name, an input price, an output price and a cached-input price. It joins the table and the exports like any other model and disappears when you reload, because nothing is stored. That is the fastest way to price a private deployment, a regional endpoint, or a negotiated rate.
Do you store my prompts or settings?
No cookies, no localStorage, no sessionStorage, no IndexedDB, no accounts. Settings live in the page's memory and reset on reload. The site has no first-party analytics. Advertising is served by Google and is described in the privacy policy; ad code cannot read the prompt because the prompt never leaves the page's JavaScript.
Why is the cheapest model not automatically the right choice?
Because the bill is only half of the cost. A model that needs two attempts, or that produces an answer a human has to fix, is more expensive than its token price suggests. Compare cost per successful task: divide the monthly figure by the share of outputs you ship without editing. Models with a 40% higher token price but a 20% higher first-pass success rate are frequently the cheaper option.
Can I use the CSV and Markdown exports in a client deck?
Yes. Both are generated in your browser from the numbers on screen, with the workload and the price date written into the file so a reader can see what was assumed. Nothing is watermarked and no attribution is required, though linking back to the calculator is welcome.