Log inSign up
Learn › Infra

V7 cuts costs 78% while boosting accuracy with GPT‑5.6 Luna

OpenAI · 27,287 views

OpenAI customer case showing 78% cost cuts with GPT-5.6 Luna while improving accuracy; concrete cost-optimization evidence.

More in Infra
57:52Infra
Serving World Models: Latency vs Throughput with NVIDIA Cosmos 3 Super on Nebius | Cosmos Labs
NVIDIA Developer · 2,896 views · Oct 2026
NVIDIACosmosserving
16:29Infra
Stop Guessing Your vLLM Config: Benchmarking LLMs on Runpod - Chris Vela, Runpod
AI Engineer · 5,266 views · Oct 2026
vLLMRunpodbenchmarking
39:48Infra
CUDA Live: Introduction to CUDA Rust
NVIDIA Developer · 9,694 views · Oct 2026
CUDARustNVIDIA