OpenAI adds discounted background mode: save 30-40% per token on GPT-6.2 with 2h/8h windows
OpenAIDevs · x · 2026-11-19
OpenAI's dev account announced public beta of discounted completion windows in Responses API background mode: for workflows that can wait, setting a 2h or 8h target for the first response on GPT-6.2 Astra or GPT-6.2 Sol cuts per-token cost by 30% or 40% versus Standard.
Suggested use case: send meeting notes before logging off and request a morning brief; reusing a continuation ID on follow-ups grants higher queue priority.
More from Infra
- EchoMoE Sends Only Deltas Between Nodes, Cutting MoE Inference Traffic 58% — sivareddyg · 2026-11-19
- JEDEC unveils DDR6 spec: 12.8 GT/s起步、最高 14.4 GT/s,带宽提升 50%,支持 128Gb 颗粒 — gnukeith · 2026-11-19
- AWS launches SageMaker JumpStart Model Leaderboard comparing 70+ models on quality, speed, cost — AWS ML Blog · 2026-11-19
- Datadog and Baseten fine-tune Qwen 3.5 9B for a 50x faster LLM summarizer — baseten · 2026-11-19
- Nvidia posts $116B quarter as analyst moves rating toward risk over unresolved uncertainties — BenBajarin · 2026-11-19
- Oracle co-CEO admits 'classic mistake' selling data centers to towns — jeremyakahn · 2026-11-19