LLM Engineering •
Claude Opus 5: Benchmarks, Pricing & Two Breaking Changes
Claude Opus 5 delivers near-Fable capability at Opus 4.8's price. Benchmarks, the real cost math, and the two API changes that break a migration.
11 min read
Read more →
LLM Engineering •
GPT-5.6 Sol vs Terra vs Luna: Which One Should You Actually Use? (2026)
GPT-5.6 Sol vs Terra vs Luna compared on price, coding, latency, and cost per task — plus a routing strategy that cuts your bill without wrecking quality.
5 min read
Read more →
LLM Engineering •
Claude Fable 5: Capabilities, Cost & When to Use It (2026)
Claude Fable 5 is Anthropic's most capable model yet. The honest deep-dive: capabilities, the $10/$50 cost math, API behavior, and when to use it.
12 min read
Read more →
LLM Engineering •
Claude Sonnet 5: Pricing, Benchmarks, Tokenizer Gotcha
Claude Sonnet 5 gives near-Opus coding at Sonnet pricing, but a tokenizer change alters your real cost. Benchmarks, pros, cons, and when to pick it.
8 min read
Read more →