GPT-6 Astra Ultrafast launches on NVIDIA Blackwell with up to 8x faster tokens
nvidia · x · 2026-10-02
NVIDIA's blog details OpenAI's new GPT-6 Astra Ultrafast mode, running on NVIDIA Blackwell GPUs with up to 8x faster token generation than Astra Standard, now available via the OpenAI API and to eligible ChatGPT Work and Codex users.
- The speedup targets agent loops: shorter edit-test-debug cycles for coding agents, less latency between tool calls, more responsive interactive apps.
- OpenAI inference lead Philippe Tillet says OpenAI's models are "exceptionally good at programming Blackwell and Rubin GPUs" thanks to NVIDIA's tooling, turning that knowledge into high-performance kernels.
- Inference optimizations continue post-deployment, so performance keeps improving.
Related event: NVIDIA Details How Blackwell GPUs Power GPT-6 Astra Ultrafast's 8x Speedup(3 posts)→
More from Infra
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS Lambda Adds GPU Support via Managed Instances for Inference and Media Workloads — DavidWells · 2026-11-19
- Nvidia Allegedly Made GPUs Artificially Scarce to Keep Prices Sky-High — GaryMarcus · 2026-11-19
- Leak Hints at Classified 1M-GPU Training Cluster in China That Skips HBM — teortaxesTex · 2026-11-19
- Tencent leaned on Japanese neocloud for AI compute; DeepSeek, Zhipu best positioned — teortaxesTex · 2026-11-19
- Open-source prefill engine for GLM-5.3-Flash beats vLLM by 3.2x on 4x B200 — CShorten30 · 2026-11-19