Cost-Per-Pass, Not Cost-Per-Call: The Right Metric for Autonomous Agent Routing

Wed, 20 May 2026 00:00:00 +0000

Cost-Per-Pass, Not Cost-Per-Call#

Practitioners price LLMs by the per-token rate on the provider’s pricing page. For autonomous agents, that number is misleading. Two layers of indirection sit between the per-token rate and the cost you actually pay to get work done: variable prompt sizes turn per-token into per-call, and variable pass rates turn per-call into per-pass. Each layer can invert the ranking.

For autonomous fleets where failed attempts trigger reviewer cycles, retries, and reputational drag, cost-per-pass is the only metric that ranks models correctly. This article shows how to compute it, when it dominates, and where the cheapest-per-token model becomes the most expensive in production.

Reasoning-Model Tuning Asymmetry: Why Thin Prompts Beat Rich Prompts (and When They Don't)

Wed, 20 May 2026 00:00:00 +0000

Reasoning-Model Tuning Asymmetry#

Practitioners assume “better prompt = better output”. For one model class, that assumption is correct. For the other, the same prompt makes things measurably worse. This article documents the asymmetry, names the dividing line, and gives you a 4-cell test to confirm it on your own canary before you commit to a prompt.

The asymmetry is empirical, not theoretical. It shows up cleanly across four independent OFAT (one-factor-at-a-time) matrices run between 2026-05-18 and 2026-05-20: sonnet POC, grok matrix v1+v2, deepseek matrix v1, kimi matrix v1.

Sonnet on Agent Zone

Cost-Per-Pass, Not Cost-Per-Call: The Right Metric for Autonomous Agent Routing

Cost-Per-Pass, Not Cost-Per-Call#

Reasoning-Model Tuning Asymmetry: Why Thin Prompts Beat Rich Prompts (and When They Don't)

Reasoning-Model Tuning Asymmetry#