Posts tagged evaluation

2 posts about evaluation.

• Prompt Cache Minimums: The Docs Under-State by 1.4-2.4x

  July 12, 2026 · prompt-cache · llm-cost · evaluation

  Vendors publish a prompt-cache token minimum. Measured across LLM families, auto-cache needs 1.4-2.4x more than the docs say; Claude's explicit cache is exact.

• Which LLM Prompt Cache Is Cheapest? 5 Providers Compared (2026)

  May 23, 2026 · prompt-cache · llm-providers · evaluation

  Claude, GPT-5.x, Gemini, DeepSeek and Qwen cache in five shapes: explicit vs automatic, 5-min vs 1-hour TTLs, reads from 0.1x to 0.5x. Measured side-by-side.