ModelsKimi K3 vs DeepSeek V4 Pro: Doing the 17x Price Arithmetic
K3 costs about seventeen times more per output token than DeepSeek V4 Pro. Here is the break-even calculation that decides whether that is worth paying.
ReadNotes on models, agents, and what inference costs
Practical writing for developers building with large language models — how they work, how to pick one, and how to keep the bill predictable.
Picking between models — and testing them on your own work.
Models
ModelsKimi K3 vs GLM-5.2: Capability Against Deployability
One is the most capable open-weight model and hard to serve. The other is MIT-licensed, leaner and built for long agent loops. How to choose between them.
Read
ModelsKimi K3: What a 2.8T Open-Weight Model Actually Buys You
Moonshot shipped the largest open-weight model yet: 2.8T parameters, 1M context, and a licence that is not MIT. A technical read on where K3 earns its price.
ReadModelsMiniMax M3 vs DeepSeek V4 Pro: Same Score, Different Models
Both land in the mid-forties on the Artificial Analysis index. They are not interchangeable, and the tie is a good lesson in why aggregate scores mislead.
ReadModelsMiniMax M3: Multimodal Agent Work From a 428B Open Model
M3 is the smallest of the frontier-class open models and the only one that takes video natively. A look at sparse attention, the licence, and where it fits.
Read
ModelsModel Routing: Send Cheap Work to Cheap Models
Most requests do not need your most capable model. Routing by task cuts cost sharply and adds resilience — here is how to build it without a mess.
Read
ModelsOpen-Weight Models in 2026: Licences, Sizes and Trade-offs
Kimi K3, GLM-5.2, DeepSeek V4, MiniMax M3 and Qwen compared on the axes that decide deployment: licence terms, active parameters, serving cost and benchmark shape.
ReadModelsQwen 3.5 for Coding: Picking a Size You Can Actually Run
The Qwen line is the only open family that spans 27B to 397B under Apache 2.0. A guide to choosing a size, reading its benchmarks, and self-hosting economics.
ReadModelsSmall vs Large Models: Why Parameter Count Stopped Meaning Much
Mixture-of-experts split model size into total and active parameters, and only one of them predicts your bill. How to think about size when picking a model.
ReadModelsStop Reading Benchmarks. Build a 20-Task Eval Instead.
Public leaderboards tell you almost nothing about your codebase. Here is how to build a private eval set in an afternoon and actually know which model to use.
ReadModelsThe Best Model for Refactoring Is the One That Stays in Scope
Refactoring is a constraint problem, not a generation problem. What the task actually demands from a model, and how to measure it on your own repo.
ReadShowing 109–119 of 119 articles