OpenAI Tests 'Pay When It Works' Pricing as Agent Fails 62% of Tasks
GaryMarcus · x · 2026-09-01
OpenAI is testing a pricing model where enterprise clients only pay when AI agents successfully complete tasks, with OpenAI absorbing compute costs for failures. Gary Marcus suggests this shift is driven by customers refusing to pay for unreliable outputs. Cited data reveals OpenAI's Operator agent fails 62% of real-world desktop tasks.
Related event: OpenAI tests outcome-based pricing: pay only when AI succeeds(4 posts)→
More from Companies & People
- Inside OpenAI's Codex Comeback: From Failed Launch to the App That Swallowed ChatGPT — every · 2026-10-16
- React veteran Eli White joins Meta Superintelligence Labs after a decade on React — Vjeux · 2026-10-16
- How the latest AI model jump is disrupting SaaS and game studio business models — The AI Daily Brief · 2026-10-16
- Joanna Shields named to 2026 Responsible Tech Guide, warns of AI adaptation gap — joannashields · 2026-10-16
- Inference startups repeat an old pattern: hype raises money, honest engineers win — gharik · 2026-10-16
- New Yorker detail: Brockman kept asking 'how do we win?' about AI safety plans — ben_j_todd · 2026-10-16