How to prompt Claude Opus 5.5, Sonnet 5.5, Fable 5.1 and Haiku 5.5
How to prompt Claude Opus 5.5, Sonnet 5.5, Fable 5.1 and Haiku 5.5: effort settings, tested prompt lines and the…
Claude Haiku 5.5 explained: a tenth of the price, if you watch the tokens
Claude Haiku 5.5 costs $0.10/$0.50 per million tokens, 90% below Haiku 4.5. What it really costs, which effort to use,…
Mistral Large 4 (Le Chonk) for marketing: the reasoning setting decides the bill
Mistral Large 4 is cheap with reasoning off and costly with it on. Prices, our own tests, EU data options…
Google’s AI content guidance: fact-check what your website actually publishes
Google now says AI-generated content should be manually fact-checked before publishing. Here is how to check the title, schema, alt…
GPT-6.1 Sol: near-Astra results at a fifth of the price
GPT-6.1 Sol keeps GPT-6 Sol's $2 and $10 token price, cuts cached input to $0.10 and scores 52 to Astra's…
Claude Sonnet 5.5 explained: same token price, cheaper cache reads, one effort trap
Claude Sonnet 5.5 keeps Sonnet 5's $2/$10 US list price and halves cache reads to $0.10. What changed, what breaks…