AI API pricing, decoded
In-depth guides on what AI APIs really cost, how to cut your bill, and which model wins for your workload.
OpenAI Prompt Caching in 2026: When the 95% Discount Pays (And When It Costs You)
On GPT-6.1 Sol and Terra, cached input is 95% off, but OpenAI now charges for cache writes. Here's the break-even point with the arithmetic, how to structure prompts to reach it, and the patterns that waste the write charge.
Top 10 Cheapest AI APIs in 2026 (Ranked by Real Cost)
Live cost ranking of the cheapest LLM APIs in 2026: per-call prices, where each model wins, and how caching, batch, long prompts and tokenizers change the order.
How to Calculate Token Cost: A Beginner's Guide
Everything you need to know about tokens — what they are, how they're billed, and how to estimate your AI API bill before you ship. With worked examples.
GPT-5.5 vs Claude Opus 4.7: Cost & Performance Comparison (and What Replaced Them)
GPT-5.5 and Claude Opus 4.7 are now previous-generation models. Their live prices side by side, what changed since May 2026, and the current equivalents to compare instead: GPT-6 Astra and GPT-6.1 Sol vs Claude Opus 5.5 and Sonnet 5.5.
OpenAI API Pricing Explained: Complete Guide for 2026
OpenAI API pricing as of late 2026: GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna, the GPT-5.x models still running, 95% cached input, the new cache-write charge, the over-272K long-context rate and the 50% Batch discount.
Claude API Pricing in 2026: How Much Does Anthropic Cost?
Current Claude API prices for Opus 5.5, Sonnet 5.5 and Haiku 5.5: which tier to pick, how prompt caching is billed (writes cost extra), Batch, Haiku 5.5's 100K-token price tier, and which older Claude models are still available.