AI Coding Field Notes

Coding agent pricing comparison: cheapest LLM API for coding, cost per million tokens, from the OpenRouter price list as JSON and CSV.

View the Project on GitHub xyzs996/llm-api-pricing

AI Costs

6 of the 32 write-ups here are tagged AI Costs. Every figure quoted below is in the figures table with the sentence it came from.

The figures

All figures, 335 rows

The write-ups

AI Programming Tool Selection Strategy: From Rapid Prototyping to Long-term Collaboration

A specialized code review agent beat Claude Code on accuracy across 200 real pull requests and 50 open-source repositories while burning about one-ninth the tokens.

Choosing the Right AI Model for Coding: Cost vs. Efficiency

Fable 5, the cheapest option at $9.05 per run, delivers only 41.2% accuracy in React projects.

MonkeyCode: The Open-Source AI Coding Platform With 900 Million Free Tokens

MonkeyCode’s free tier includes 900 million tokens, deploys to your own network with 1 command, and ships as open source you can read.

The Hidden Costs of GPT-5.6 Model Selection: A Developer’s Real-World Guide

“Choosing the right GPT-5.6 model for your business is more about avoiding cost overruns than just picking the cheapest option.”

Token Optimization for Indie Developers’ AI API Bills

In July 2026, while indie developers building AI coding products full-time watched their API burn rate climb toward their revenue, a quieter shift in the Chinese developer stack showed a different…

When AI Customer Service Backfired: Klarna’s Case and the Four-Stage Path to Enterprise AI Adoption

Klarna reported $4 million a year in savings and a 99.96 percent conversation engagement rate, the kind of pair of numbers that ends an internal debate before it starts.


All 32 write-ups


Did this answer it? A star on the repository is the whole ask — it is what puts these in front of the next person looking; the data is CC BY and does not require starring.

Want a figure that is not here yet? Say which metric, which provider, which unit — one required field, and the page you came from is already filled in.

Got a better number? Open an issue — corrections and counter-data are the point.