---
title: "NeverPayTwice (@neverpaytwice) | Hashnode"
description: "Free, tested guides and MIT scripts on real AI token usage and API costs. Read the latest articles by NeverPayTwice on Hashnode."
url: "https://hashnode.com/@neverpaytwice"
---

@neverpaytwice

# NeverPayTwice

@neverpaytwice · Joined November 2026

Free, tested guides and MIT scripts on real AI token usage and API costs.

### [Claude Code: subscription or API? Work it out from your own logs](https://neverpaytwice.hashnode.dev/claude-code-subscription-or-api-work-it-out-from-your-own-logs?utm_source=hashnode&utm_medium=feed)

Originally published at neverpaytwice.com. Short answer: price one month of your real Claude Code usage at API rates and put it next to the plan price. If the API figure is lower than the plan, paying

5 min read · [neverpaytwice.hashnode.dev](https://neverpaytwice.hashnode.dev/claude-code-subscription-or-api-work-it-out-from-your-own-logs?utm_source=hashnode&utm_medium=feed)

[3](https://hashnode.com/posts/claude-code-subscription-or-api-work-it-out-from-your-own-logs/6afc964723bcee5798db1b0e) [3d ago](https://hashnode.com/posts/claude-code-subscription-or-api-work-it-out-from-your-own-logs/6afc964723bcee5798db1b0e)

### [Does Claude prompt caching save money? The break-even math](https://neverpaytwice.hashnode.dev/does-claude-prompt-caching-save-money-the-break-even-math?utm_source=hashnode&utm_medium=feed)

Originally published at neverpaytwice.com. Short answer: usually yes, by a lot, but not always. Writing a prompt to the cache costs more than sending it normally (1.25× the input price for the 5-minut

7 min read · [neverpaytwice.hashnode.dev](https://neverpaytwice.hashnode.dev/does-claude-prompt-caching-save-money-the-break-even-math?utm_source=hashnode&utm_medium=feed)

[2](https://hashnode.com/posts/does-claude-prompt-caching-save-money-the-break-even-math/6afb35210eb6ca71dd1eae50) [4d ago](https://hashnode.com/posts/does-claude-prompt-caching-save-money-the-break-even-math/6afb35210eb6ca71dd1eae50)

### [Claude thinking tokens: what they cost and how to spend less](https://neverpaytwice.hashnode.dev/claude-thinking-tokens-what-they-cost-and-how-to-spend-less?utm_source=hashnode&utm_medium=feed)

Originally published at neverpaytwice.com. Short answer: thinking tokens are billed as output tokens, at the output price, whether or not you see them. On the newest Claude models thinking is on by de

5 min read · [neverpaytwice.hashnode.dev](https://neverpaytwice.hashnode.dev/claude-thinking-tokens-what-they-cost-and-how-to-spend-less?utm_source=hashnode&utm_medium=feed)

[4d ago](https://hashnode.com/posts/claude-thinking-tokens-what-they-cost-and-how-to-spend-less/6afb020803eb8f97b30da429)

### [Claude Batch API: half price, if you can wait](https://neverpaytwice.hashnode.dev/claude-batch-api-half-price-if-you-can-wait?utm_source=hashnode&utm_medium=feed)

Originally published at neverpaytwice.com. Short answer: Anthropic's Message Batches API charges 50% of the standard price on all usage: input, output, cache writes and cache reads. You send up to 100

6 min read · [neverpaytwice.hashnode.dev](https://neverpaytwice.hashnode.dev/claude-batch-api-half-price-if-you-can-wait?utm_source=hashnode&utm_medium=feed)

[5d ago](https://hashnode.com/posts/claude-batch-api-half-price-if-you-can-wait/6afa06672a972cb070302f36)

### [Why is my Claude API bill so high? 9 things to check](https://neverpaytwice.hashnode.dev/why-is-my-claude-api-bill-so-high-9-things-to-check?utm_source=hashnode&utm_medium=feed)

Originally published at neverpaytwice.com. Short answer: the usual causes are thinking tokens you never see but pay for as output, a prompt cache that silently never hits, the whole conversation being

7 min read · [neverpaytwice.hashnode.dev](https://neverpaytwice.hashnode.dev/why-is-my-claude-api-bill-so-high-9-things-to-check?utm_source=hashnode&utm_medium=feed)

[5d ago](https://hashnode.com/posts/why-is-my-claude-api-bill-so-high-9-things-to-check/6af9ed57475550e5c450794a)
