Opus 5's five lines, and the agent loop against Sonnet.
The rate card is read in this tab. Nothing is uploaded and no model API is called.
Last updated 2026-09-22 Source
Versus Claude Sonnet 5: $4.88 more than Claude Sonnet 5. Claude Sonnet 5
Opus 5 is the card people mean when they say the expensive Claude. Sonnet 5 is the sibling this site puts next to it. The useful question is not the input line in isolation. A fifty-turn loop rewrites or rereads the same prefix, so once the hit rate is high the cache-read line and the two write lines move the total more than the headline input rate. There is no long-context tier to remember: the window is one schedule the whole way. This page puts Opus next to Sonnet on that loop and leaves the batch factor on the card, where you can see it, instead of folding it into the total and pretending a batch job and an interactive session are the same purchase.
The numbers on this page are not typed in. A checked rate card lives in one table, and every figure you see is read from that table or returned by the cost function the rest of the site calls. The scenario is agent-loop-50: fifty turns, one cacheable context that comes back every turn, a little new input that is never cached, and output on every turn. The three totals further down set the cache hit rate at zero, one half, and nine tenths. Hit rate is the share of that repeated context that is read from cache instead of written again. It is not a discount applied after the fact, and it is not the batch factor. Batch, when the card has one, is listed on the card and is left out of these totals on purpose, because a batch job is a different purchase from the interactive loop. When a card publishes no price for a cache line the scenario still has to account for, those tokens are billed as fresh input and the result is marked so. That is a property of the card, not a missing feature of the page. A long-context tier, when the card has one, applies to a single request whose prompt is over the threshold. The fifty short turns of this loop stay on the base tier, which is why a model with a long-context tier still shows one set of loop totals. The worked example below names the day the card was confirmed against the vendor page linked next to it. If you need a different loop, the parent page has the other three scenarios and a slider.
Rates on this page were checked against the vendor pricing page on 2026-09-22.
0% cache hit: $13.88 50% cache hit: $8.13 90% cache hit: $3.52
Versus Claude Sonnet 5: $4.88 more than Claude Sonnet 5.
It is the day this card was checked against the vendor pricing page. It is not the model's release day, and it is not a promise that the vendor has not changed a number since. When the card changes, the date changes with it.
This card publishes cache read, a five-minute cache write and a one-hour cache write, plus a batch factor. It does not publish a long-context tier, so a full window is the same five lines as a short prompt. The one-hour write is a different product from the five-minute write, not a longer spell of the same line.
Sonnet is the card you would move a long loop onto. Same five lines, no long-context tier on either side. The delta at a high hit rate is the interesting one, because that is when the write lines stop dominating.