Peter Steinberger's 100 AI agents racked up $1.3 million in OpenAI tokens in 30 days building OpenClaw

"Steinberger posted a screenshot of the bill on X, showing $1,305,088.81 charged to the OpenAI API, with GPT-5.5 as the primary model. OpenAI is covering the cost: Steinberger joined the company in February 2026, and the spending is treated as a research investment in understanding what software development looks like when token economics are not a limiting factor."

"The bill, which covered 603 billion tokens across 7.6 million requests over 30 days, is the most visible demonstration yet of what happens when AI-powered software development is run without budget constraints, and of how quickly costs escalate when autonomous agents operate continuously at scale."

"The 100 Codex instances are not simply generating code. Steinberger's three-person team has built an autonomous development pipeline in which AI agents perform a range of tasks that would ordinarily require a much larger engineering organisation. The agents review pull requests, scan commits for security vulnerabilities, deduplicate GitHub issues, write fixes, and open new pull requests based on the project's broader roadmap."

"Others monitor performance benchmarks and flag regressions to the team's Discord server. Some agents, according to The Decoder, even attend meetings and generate pull requests for features that come up in conversation. The team also uses Clawpatch.ai, Vercel's Deepsec, and Codex Security for additional"

A creator of OpenClaw spent $1.3 million in OpenAI API costs over 30 days by running roughly 100 Codex instances simultaneously. The bill totaled 603 billion tokens across 7.6 million requests, with GPT-5.5 as the primary model. OpenAI covered the charges after the creator joined the company, treating the spending as a research investment into software development without token-economics constraints. The system uses an autonomous development pipeline where agents review pull requests, scan commits for security vulnerabilities, deduplicate GitHub issues, write fixes, and open new pull requests aligned with the project roadmap. Additional agents monitor performance benchmarks, flag regressions, and may generate pull requests based on meeting discussions.

Read at TNW | Apps