The creator of OpenClaw spent $1.3 million on OpenAI API tokens in a single month. The bill covered 603 billion tokens across 7.6 million requests from 100 Codex instances. The top model used was GPT-5.5, dated April 23, 2026.
Developer shares API dashboard screenshot
The developer posted a screenshot of his API usage dashboard showing $1,305,088.81 in spending over 30 days. On the day he shared the screenshot, his account logged $19,985.84 in spend and 206,000 requests. The high cost was partly due to Fast Mode pricing. Disabling Fast Mode would reduce the raw API cost to around $300,000.
The $1,305,088.81 spend equates to roughly 60 Codex Pro subscriptions at non-fast-mode pricing. The fleet of Codex agents autonomously reviews pull requests, scans commits for security vulnerabilities, deduplicates GitHub issues, and writes fixes. Some agents open PRs based on the project's broader roadmap, while others monitor performance benchmarks and flag regressions.
According to Tom's Hardware and The Decoder, the agents also attend meetings and generate PRs for features that come up in conversation. The developer noted that the latest CodexBar update renders API costs way nicer. OpenAI has not commented on the usage.
Discussion
0 comments
Log in to join the thread with a thoughtful take, question, or correction.