Oct 2, 2026

API relay reliability checks

A repeatable relay acceptance flow: fix the request first, then inspect time to first byte, stream completion, error classes, and retry boundaries.

Read article

Reader submissions

modelsOct 2, 2026

Claude Opus 5.5 specs, list prices, and published benchmarks

modelsOct 2, 2026

Claude Sonnet 5.5 specs, list prices, and published benchmarks

modelsOct 2, 2026

GPT-6.1 Sol specs, long-context prices, and published comparisons

ModelsOct 2, 2026

Grok 4.7 specs, long-context prices, and published benchmarks

Articles

9 articles
  1. How to evaluate an AI relay for software engineeringChecks for code generation, agent tool chains, long context, and cache protocol behavior when a relay sits in a software-engineering workflow.Sep 17, 2026
  2. Stop trusting a 99% uptime claim: the AI API relay failures we hit, and how we test stabilityStarting from fake 200s, truncated streams, and nighttime stalls, this is how the stability metrics and tests that actually decide production experience are defined.Sep 17, 2026
  3. From translationese to a felt native voice: three years of Chinese writing with AI, and with API relaysA Chinese writer’s three-year record of using models, and of bringing those models into a daily writing flow through an API relay.Sep 17, 2026
  4. The gray-market ghost in model relays: founders burned by a 10% APIAnonymous cases about model swapping, billing traps, context truncation, and data risk behind very cheap relays.Sep 17, 2026

New articles will appear as they are published.