Theo charts how Claude and Codex models behave in his own requests and argues AI coding is getting cheaper, not more expensive
I collected all of my requests to Claude and Codex and put them in a clickhouse db. The data is so fun to play with
Context
A popular developer's hands on data and arguments add color to the debate over AI coding costs, subscription plans and whether heavy agent use at labs like Anthropic is sustainable.
Theo Browne runs the t3.gg developer channel and the T3 Code app, and these three posts are his own opinions and personal data rather than lab announcements. The chart comes from his own requests to Claude and Codex, and its footnote says models with under 5,000 requests are noisy. Two of the posts quote others: one quotes a critic of Anthropic's code change volume, and one quotes his own earlier post about the cost of $200 subscriptions.
Deep dive
On October 14, Theo posted that he collected all of his requests to Claude and Codex in a ClickHouse database and that the data is fun to play with. The attached dashboard compares models on several habits. Anthropic's Haiku 5.5 leads output speed at 140 tokens per second, while the GPT models shown range from 29 to 51. Claude models use grep instead of rg in 91% to 100% of cases, against 2% or less for GPT models, while GPT 6.1 Sol runs git status 14.4 times per commit and GPT 5.5 makes parallel tool calls in 52% of responses. Opus 5 takes the most steps per turn, at 33.
In a second post, Theo mocked a critic who said Anthropic's 30,000 code changes per day was absurd by 3 or 4 orders of magnitude, writing that the critic thinks a 2,000 person company should be merging under 30 pull requests a day. The critic, Jim Stewartson, had predicted Anthropic's codebase would start cracking. Anthropic's 30,000 figure was covered in the October 13 deck.
In a third post, Theo answered people asking whether $200 plans will last as AI gets more expensive. He wrote that AI is getting cheaper and the $200 plans will get better over time, adding that OpenAI does not count right now. He quoted his own earlier joke that for the cost of 8 years of $200 Claude subscriptions, a team could run poorly quantized DeepSeek V4 Flash at 30 tokens per second.
The chart reflects one heavy user's workflow, so it shows style differences rather than which model is better.
What to expect next
Watch whether other developers publish similar logs of their agent requests, which would show whether the habits in Theo's chart hold across different codebases and workflows.
Also watch pricing for the $200 a month tiers at Anthropic and OpenAI, and whether labs keep adding usage to those plans as Theo predicts, or tighten limits as heavy agent use grows and compute costs rise.