Roundup 01
Best LLM APIs with a free tier (2026)
Which LLM APIs are actually free to call in 2026 — not free chat apps or expiring trial credits. Verified free tiers, real rate limits, and the data catch.
Journal Independent editorial
The journal.
18 posts across analysis, opinion, how-to, research, and roundups.
18
6
16min avg
About
Independent analysis, opinion, and how-to coverage of LLM tooling -- written for engineers who pay the bill. No paid placements, no vendor talking points, no benchmarks lifted from press kits. Every model price comes from the vendor's own page, verified the week of publication; every cost calculation shows its math. The blog sits next to the price desk and the comparisons -- prose covers the questions a table cannot answer (when does a 90% cache discount stop mattering? which workload class breaks GPT vs Claude pricing parity?). Cornerstone analysis ships first; opinion, tools how-to, research summaries, and roundups will join as the catalogue grows. Read for the math, stay for the disagreements.
§ Filter by category
Category
Showing 6 of 18 posts — page 2 of 2
Analysis 02
Hidden LLM API costs nobody quotes (2026)
The $/M input/output sticker hides cache-write premiums, a tokenizer tax, context surcharges, invisible reasoning tokens, and more. Ten verified costs, with proofs.
Analysis 03
The reasoning dial nobody touches: why your thinking-model bill is so high
In 2026 the biggest lever on your LLM bill isn't which model. It's how hard the model thinks: reasoning tokens bill as output, and most models think by default.
Roundup 04
The cheapest LLM API by use case (2026)
There is no single cheapest LLM API. The winner depends on your workload shape. Verified $/M prices for classification, chat, coding, RAG, batch, and reasoning.
Tools Howto 05
Caveman mode for Claude Code: the math behind the 65% headline
Caveman mode strips filler from Claude's output. The 65% headline is real for output tokens. Here's what it actually saves on your monthly bill.
Analysis 06
How prompt caching actually changes the LLM cost math
Anthropic charges 10% of input for cache reads, with a 1.25x write fee. OpenAI auto-caches above 1024 tokens. The math changes which LLM is cheapest -- here is when.