Inference Costs Halved but Quotas Tightened?
mark_k · x · 2026-07-12
This post questions a claim about OpenAI:
> "OpenAI engineers just halved its inference costs."
The author finds it ironic because, simultaneously, many on X are complaining that OpenAI has tightened the usage limits for GPT-5.6, making it feel like "inference is getting more expensive."
Citing The Information, the post notes that OpenAI engineers halving inference costs is their closely guarded "secret weapon," fearing that leaks would allow other labs to optimize their own costs.
Related event: GPT-5.6 Sol Silently Nerfed, OpenAI Confirms Rollback(8 posts)→
More from Infra
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- Revenue per GPU can rise as token prices fall, argues Gavin Baker — GavinSBaker · 2026-10-27
- Anthropic S-1: only $19B total compute spend since inception, overbuild warning — bookwormengr · 2026-10-27
- CoreWeave, You.com and NVIDIA lift BrowseComp 22.9% in 3-week RL post-training sprint — RichardSocher · 2026-10-27
- Grid queues make power architecture an AI-factory decision; Exowatt and Redwood offer fixes — ingliguori · 2026-10-27
- Two CVSS 9.9 Wasmtime flaws allow sandbox escape, one ARM64-only since 2020 — basedjensen · 2026-10-27