Epoch AI: GPT-6.1 Sol halves cached-input pricing, runs long prompts faster
Jsevillamol · x · 2026-10-10
Epoch AI's measurements show OpenAI halved cached-input prices for GPT-6.1 Sol versus GPT-6 Sol, while also speeding up long-prompt handling — suggesting a new architecture under the hood.
More from Infra
- Uncensored Qwen-Image-2.1-Turbo GGUF quants released, refusal drops to 1.2% — udmrzn · 2026-10-11
- Developers ditch self-hosting for Fireworks AI and Tinfoil, says iamtrask — iamtrask · 2026-10-11
- Bittensor miners squeeze up to 54% more inference throughput from the same GPUs — bittingthembits · 2026-10-11
- SkyPilot meetup recap: GPU scheduling pain, Holo4 training on K8s, and SGLang's roadmap — skypilot_org · 2026-10-11
- PyTorchCon talk: MoRI + vLLM brings RDMA KV-cache transfer and wide expert parallelism to AMD — PyTorch · 2026-10-11
- ODS V3 pre-release turns any PC, Mac or Linux box into a private AI server — tom_doerr · 2026-10-10