Coding agent pricing comparison: cheapest LLM API for coding, cost per million tokens, from the OpenRouter price list as JSON and CSV. An AI model token price comparison repriced at a real agent mix — 95.6% cached input pricing, 6.5x off list: prompt caching price, cache read price, cache hit share, long context pricing, DeepSeek peak/off-peak.
3 of the 68 write-ups here are tagged Developer Productivity. Every figure quoted below is in the figures table with the sentence it came from.
If you’re hitting the 5-hour Codex limit like clockwork every day, stop counting minutes.
“If your AI keeps writing bad code, you need a better model.” In each of the rebuilds below, a new model wouldn’t have fixed anything, because the model was reading the wrong thing.
When the Claude Code team decided to slash 80% of their system prompts, most developers expected the model to lose its edge in complex engineering tasks.
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.