|

A dark editorial illustration of three identical glowing cubes on pedestals of different heights, representing the same coding model costing three different amounts depending on its harness

The Harness Sets The Bill: Same Model, Same Tasks, Up To 3x The Cost, And No Accuracy Gain

Posted on October 28, 2026October 28, 2026 by Clara Milicent

Two studies found harness choice barely moves coding-agent accuracy while cost per task differs up to three times, and up to five times. What to measure.

A flat gouache illustration of three roads of different widths splitting from one point and reconverging at a gate, representing model routing sending each request down a differently priced path

Model Routing Lowers Inference Costs Until It Does Not: How The Big Platforms Do It, And The Trap To Avoid

Posted on October 25, 2026October 25, 2026 by Clara Milicent

Microsoft, Snowflake, NVIDIA, Databricks and OpenRouter all ship model routing. How each decides, what the savings really look like, and the Pareto trap.

An abstract dark editorial illustration of stacked translucent layers with a single bright vertical light, representing the compressed checkpoint and benchmark gains in DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017: What The Pareto Upgrade And Open Search API Change For Builders

Posted on October 17, 2026October 21, 2026 by Clara Milicent

DeepSeek V4.1 Flash 1017 adds benchmark gains under the same model name and MIT weights, and opens Search and Fetch at 0.75 dollars per 1,000 calls. What changes.

$A linocut print of a small dense cube beside a large outlined cube, showing what Haiku 5.5 delivers at a fraction of the size$

Claude Haiku 5.5 Cuts Prices Up To 90 Percent: What The Cheap Tier Of AI Now Does

Posted on October 15, 2026October 15, 2026 by Clara Milicent

Anthropic’s Claude Haiku 5.5 costs 10 cents per million input tokens under 100k, with cache reads at a cent and an adjustable effort setting. What it changes.

Gemini 4 Argon API pricing falling, shown as descending bars and a downward trend line

Gemini 4 Argon Opens Up at $2 per Million Tokens: What the New API Pricing Changes for Builders

Posted on October 15, 2026October 15, 2026 by Clara Milicent

Google’s Gemini 4 Argon reaches paid API customers at an introductory $2 per million input tokens and $10 per million output, with cached input 95 percent off. What it changes for builders.