# What this website cost to build

Every AI request made while building eduarddziak.com, measured from local session logs and priced at published API rates.

> Source: https://eduarddziak.com/build-cost/
> Period: 2026-07-31 to 2026-08-07
> Updated: 2026-08-07
> Data: /data/build-cost.json and /data/build-cost.csv
> Licence: CC BY 4.0

## Summary

| Measure | Value |
| --- | --- |
| Total estimated cost | $377 |
| Total tokens | 412,576,307 |
| Requests | 1,270 |
| Days worked | 7 |
| Saved by caching | $2,261 |
| Period covered | 2026-07-31 to 2026-08-07 |

## By week

| Week | Cost (USD) | Tokens | Running total (USD) |
| --- | --- | --- | --- |
| 2026-W31 | 114.52 | 100,808,169 | 114.52 |
| 2026-W32 | 262.60 | 311,768,138 | 377.12 |

## By tool

| Tool | Cost (USD) | Tokens | Records |
| --- | --- | --- | --- |
| Claude Code | 191.03 | 256,650,983 | 1257 |
| Codex | 186.09 | 155,925,324 | 13 |

## Where the money goes

| What the tokens were doing | Cost (USD) |
| --- | --- |
| Re-reading earlier context | 253.41 |
| Writing answers and code | 47.18 |
| Storing context for reuse | 40.23 |
| New instructions and files | 36.30 |

## Questions

### How much does a website cost to build with AI?

This one has cost $377 so far in AI usage, across 1,270 requests over 7 working days. That splits into Claude Code at $191 and Codex at $186. The figure covers all of the design, content, code, SEO and release work done with AI assistance on this site.

### Is that an actual bill?

No. Both tools ran on monthly subscriptions, which charge a flat fee rather than charging per token. This figure is what the same work would have cost at the published pay as you go rates. It is a fair way to compare one week against another, not an invoice.

### Why is the token count so much larger than the cost suggests?

Because 98% of the tokens are context being read again rather than written fresh. Every time an assistant continues a conversation it re-reads everything that came before. Cached re-reading is billed at a tenth of the normal input rate, so a very large token count can still carry a modest cost.

### What did caching actually save?

$2,261. Without caching the same work would have cost $2,638 rather than $377, roughly 6.0 times more. It is the single largest cost decision in the project, and it is on by default.

### Which tools and models are counted?

Claude Opus 5 and GPT-5.6 Sol, used through Claude Code and Codex. Work done in the Claude or ChatGPT web apps is not counted, because those apps do not record token usage on this machine.

### How accurate is this?

The token counts are exact. They are what each service reported for each request, not an estimate worked back from the text. Prices come from the official published rate cards for each provider, and are reviewed regularly so the totals follow any change. One figure is an assumption. OpenAI charges more past a context size it does not publish, so a boundary of 128,000 tokens is assumed. Claude has no such surcharge.

### How often does this page update?

Every figure on this page is generated from the collected data, so the dates and totals move with it rather than being written by hand. It currently covers 31 July 2026 to 7 August 2026. Collection runs regularly because the source logs are deleted after 30 days, so anything not captured inside that window is lost for good.

### Does the published data contain anything private?

No. Only dates, token counts, model names and totals are published. No prompt, no message content, no file name, no file path and no session identifier is read by the collector or written to the dataset. You can check that by opening the JSON or CSV.

### Can I reuse these numbers?

Yes. The full dataset is published as JSON and CSV at stable addresses under a Creative Commons Attribution licence. Attribution to eduarddziak.com is all that is asked.

## How this is measured

Every figure comes from the session logs that Claude Code and Codex write on the machine this site is built on. Each request records what it used, so the token counts are measured rather than estimated. The same request appears in several log files when a session is resumed, so records are matched on their request identifier and counted once. Without that step the totals roughly double. Codex reports a running total for a whole session rather than one figure per turn, so only the final figure of each session is taken. No prompt, message, file name or file path is read or stored. Only counts, model names and timestamps.

OpenAI charges a higher rate past a context boundary it does not publish. This figure is an assumption. A boundary of 128,000 tokens is assumed, and each Codex turn is classified on its own size so a session is blended across both rates rather than forced onto one of them. Claude has no long-context surcharge. Models 4.6 and later bill the full context window at standard rates. Published API list prices. Subscription plans do not bill per token.