Rates checked September 30, 2026

Claude Token Cost Calculator

Each rate in the card below opens the Anthropic page it was read from.

Two numbers decide most Claude bills: how many tokens you send, and how many the model sends back. This page turns either one into dollars, using the same rate card that sits on our home page.

Price a prompt, or see what a budget buys

Per-token prices are hard to feel. Paste text and this page estimates what it will cost. Put in a token count and it prices it. Put in a budget and it tells you how far that budget goes.

Estimate tokens from text

Claude Sonnet 5.5 Cheaper
Estimated tokens—
Cost as input—
Claude Opus 5.5 Cheaper
Estimated tokens—
Cost as input—

Counting at roughly four characters per token for English. That is an estimate, not a count — we don't ship Anthropic's tokenizer, and a character rule is not one. Code, logs and non-English text break the rule in both directions. Nothing you paste here leaves your browser.

Price a token count

Presets
Claude Sonnet 5.5 Cheaper
Input cost—
Output cost—
Per request—
Claude Opus 5.5 Cheaper
Input cost—
Output cost—
Per request—

The support-bot preset — 2,000 input, 500 output — costs $0.009 per request on Sonnet 5.5 and $0.018 on Opus 5.5. Both figures come from the rate card below, so they move when it moves.

Reverse a budget

Claude Sonnet 5.5 Buys more
Input tokens—
Output tokens—
Claude Opus 5.5 Buys more
Input tokens—
Output tokens—

Formula, everywhere on this page: tokens ÷ 1,000,000 × the price per million tokens. Everything here is list price, and it excludes caching, batch discounts and any negotiated rate.

How Claude token pricing works

Anthropic bills Claude by the token, and a token is not a word. It is a chunk of text, usually a few characters long. Every exchange is billed twice: once for what you send, once for what comes back. Output costs five times input on both models, which is why a paragraph the model writes costs more than a paragraph you paste in.

The card below is the only price list on this site. The calculator above reads it directly, so the two cannot drift apart: change a number in the table and the estimate follows, with no second copy to keep in step. Haiku 5.5 has been announced but not priced, so its row stays blank on purpose — a blank cell is honest, a guessed one is not.

Three things move a bill more than people expect. Volume, because every price here is per million tokens. Output length, because that is the expensive side. And caching, which has its own section further down.

Model Input Output Cache read Cache write (5 min)
Claude Sonnet 5.5
checked 2026-09-30
$2.00 $10.00 $0.20 $2.50
Claude Opus 5.5
checked 2026-09-30
$4.00 $20.00 $0.20 $5.00
Claude Haiku 5.5 — — — —

Rates above are US dollars per million tokens, billed on Anthropic's direct API. Last verified September 30, 2026.

Claude Haiku 5.5 has no published price, so it has no date here and no number. A blank row is a statement: we could not source it.

Claude token cost, by amount

Nobody budgets in millions of tokens, so here are the round numbers, priced at both rates for input and output separately.

Tokens Sonnet 5.5 input Sonnet 5.5 output Opus 5.5 input Opus 5.5 output
1,000$0.002$0.01$0.004$0.02
10,000$0.02$0.10$0.04$0.20
100,000$0.20$1.00$0.40$2.00
200,000$0.40$2.00$0.80$4.00
500,000$1.00$5.00$2.00$10.00
1,000,000$2.00$10.00$4.00$20.00

Each figure is the published rate divided by a million and multiplied by the token count — the same arithmetic the calculator runs. These are uncached input and output; a stable prefix you resend is cheaper, which the caching section covers. Note the shape of the numbers: output is five times input, so a long answer costs more than a long question.

How caching changes Claude token cost

Prompt caching is the one lever that changes a bill without changing the work. Two prices do all of it. Writing a prefix into the cache costs 25% more than sending it as ordinary input: $2.50 against $2.00 on Sonnet 5.5, $5.00 against $4.00 on Opus 5.5. Reading it back costs $0.20 on both — a tenth of Sonnet's input rate, a twentieth of Opus's.

The trade pays only on repetition. Send a prefix once and you have paid the write premium and collected nothing on it. Send it twice and you are already ahead. Send it ten times and the input line costs about a fifth of what it would have: $4.30 for ten uses of a one-million-token prefix, against $20.00 uncached. The saving climbs towards ten times the longer you repeat, but ten times is the ceiling — reaching it means reusing the same prefix more or less forever.

Two details decide whether it works for you. Cache entries expire, and the write price above is for the five-minute cache. A prefix that shows up once an hour can expire between uses, and then you have paid the premium for nothing. And the premium lands on write, so a workload that sends a different document every time does worse than one that never turned caching on. The workloads that win are dull: a fixed system prompt, fixed instructions, the same reference material on every call.

Counting Claude tokens: what we can and can't do

We estimate token counts; we don't count them. The difference matters, so the box at the top of this page says it plainly rather than burying it in a footnote.

The rule of thumb is four characters per token for English prose. It holds up reasonably well on ordinary sentences and falls apart on everything else. Code, JSON and logs usually run fewer characters per token, because punctuation and short identifiers split into more pieces than plain words do. Accented and character-based languages run the other way, well over four. A mixed document can be wrong in both directions at once.

When the exact number matters — sizing a batch job, or checking whether a prompt fits inside a context window — call Anthropic's count_tokens endpoint against the same model you will actually use. It returns the real count for the real text, and it is free to call. Treat our estimate as a budgeting aid, not as a limit check.

Claude token cost: common questions

$0.02 on Sonnet 5.5 input and $0.10 on Sonnet 5.5 output. On Opus 5.5 the same 10,000 tokens cost $0.04 input and $0.20 output. Prices are per million tokens, so 10,000 tokens is one hundredth of the published rate.
About 2.5 million Sonnet 5.5 input tokens, or 500,000 Sonnet 5.5 output tokens. On Opus 5.5, $5 buys 1.25 million input tokens or 250,000 output tokens. The gap is the 2x rate difference, not a rounding error.
$0.40 as Sonnet 5.5 input, or $2.00 as Sonnet 5.5 output. The same 200,000 tokens cost $0.80 input and $4.00 output on Opus 5.5. To picture it: about two novels' worth of text, at our four-characters-per-token rule of thumb.
Roughly, for English. Both products split words into sub-word pieces and both land near four characters per token, which is why the same paragraph prices out similarly on either. The counts still differ per model, so price your own text against the model you will actually call rather than a general rule.
Yes, on the read side. A cache read costs $0.20 per million tokens on both models, against $2.00 on Sonnet 5.5 and $4.00 on Opus 5.5 for fresh input. Writing the cache costs more than fresh input once — $2.50 and $5.00 — so caching pays from the second use of a prefix onwards, not the first.
Every priced row carries the date it was last checked, and each figure opens the Anthropic page it came from. We verify against the source page rather than an aggregator, and we audit the whole table once a month.

How we check these rates

Every figure in the card above was read from Anthropic's own announcement page for that model, and the link inside each cell goes to the page the number came from — not a summary, not an aggregator, not somebody else's cached table. Each priced row carries its own check date, and the note under the table carries the date of the last full audit.

Where we cannot source a figure, the cell stays empty. Haiku 5.5 is the current case: announced, not priced. Prices move when a model ships or is re-priced, not on a schedule, so we re-read on announcements and audit the full table monthly.

This page covers cost only. Model choice, context windows and the wider billing picture are on our home page.