From the Dracon workshop
We maintain structured catalogs of AI providers, games, music, and tools — these articles are written from that data, not from vibes. When the data changes, the articles get regenerated.
- The cheapest way to run Claude right now: every route in our catalog, from $0 to $200 a month Seven providers we track serve Claude. Free lanes, pay-as-you-go, and subscriptions compared, with the catches and the cheapest route for light vs heavy use.
- AI promo codes that actually work (August 2026): all 15 we track, what they get you, and the catches Our catalog tracks 15 active AI promo and referral codes across 13 providers. What each one gets you, the fine-print limits, and which are worth the effort.
- Free AI API rate limits, compared: which free tiers can do real work and which are demo taps 22 of the 42 AI providers we track have a free tier. The real limits side by side: RPM, daily caps, token grants, and the 7 that hold up for actual work.
- What bring-your-own-key actually costs: the real math The honest math behind bring-your-own-key: real API token prices from our 42-provider catalog versus $20 AI subscriptions, and why Dracon Omni is $10.
- One person, one platform: how dracon.uk actually runs An honest ops tour of dracon.uk: one VPS, five static apps and two Node apps behind Caddy, five Rust APIs on unix sockets, Paddle, OVH buckets, one person.
- We published 5 novels written by our own book pipeline Five novels, 523,980 words, written end to end by our own book pipeline and published free forever with the AI label on the tin. Meet the Dracon Bookstore.
- How a game ships to the Dracon arcade: build, bucket, catalog flip The 8-step pipeline from local build to OVH bucket to the catalog flip, the real status counts across our full 16-game catalog today, and what ships next.
- Three games, one bug: the SvelteKit hosting bug that broke our arcade One SvelteKit default broke three of our games on the same night: 390 to 451 reloads in six seconds, zero console errors. The full postmortem, with the fix.
- What 1,000 tracks of focus music have in common: we ran the numbers We computed the real stats behind our 1,000-track focus library: BPM bands, mood-tag counts, the 10-track rule, and why only 3 cooks in 100 carry the focus tag.
- Music to fall asleep to, built from recipes Seven sleep-friendly cooks from our 1,000-track recipe library: a 40 BPM space drift, a note held for hours, dark ambient with a shadow, and honest caveats.
- The AI price war went nuclear this week: DeepSeek V4 Flash at $0.14/M tokens and GPT-5.6 Luna down 80% — in the same 24 hours OpenAI cut GPT-5.6 Luna 80% on July 30; DeepSeek shipped V4 Flash to public beta July 31 from $0.14/M tokens. We track 42 AI providers — here's what changed, with numbers.
- 22 of the 42 AI providers we track have a free tier. Only 7 are actually useful. We maintain rate-limit data on 42 AI providers. Most 'free tiers' are demo taps. These 7 hold up for real work — with actual limits and how to mix them via BYOK.
- 16 games in the pipeline, 1 playable today: an honest state of the Dracon arcade Our games catalog tracks 16 projects from playable to candidate. What each status means, what's playable now, and why we publish the pipeline honestly.
- 1,000 tracks, 100 mixes, 82 mood tags: we built a free focus-music library and kept the receipts The Dracon music library is 1,000 generated tracks in 100 curated 'cooks', every recipe kept. The data behind it and how to use it.
- Where do your AI keys go when you use our tools? A straight answer BYOK tools ask for the most sensitive string you own. Exactly what happens to your keys across Dracon tools — extension, chat, vault — and what we never do.