How NVIDIA GPUs Help Accelerate OpenAI’s GPT-6 Astra Ultrafast

GPT-6 Astra Ultrafast is available now in the OpenAI API and to eligible ChatGPT Work and Codex users, running on NVIDIA Blackwell GPUs. According to NVIDIA, the model is accelerated by inference optimizations through OpenAI's models that tap into the capabilities of the NVIDIA Blackwell architecture. Ultrafast offers up to 8x faster token generation than the Astra Standard mode.

For developers, NVIDIA says faster generation can shorten coding agents' edit-test-debug cycles, reduce time spent generating responses between tool calls and make interactive applications feel more responsive. The company describes the benefit as mattering most when a response is repeated across a workflow in which an agent writes code, uses a tool, checks the result and decides what to do next.

Philippe Tillet, inference lead at OpenAI, said NVIDIA's investment in tooling and documentation has enabled OpenAI to make its models exceptionally good at programming Blackwell and Rubin GPUs. He said Astra can turn that knowledge into high-performance kernels, and that with Astra Ultrafast this means faster model responses as agents write code, use tools and work through complex tasks.

NVIDIA also said performance gains continue after deployment: OpenAI is using its own models to help refine the inference software running on NVIDIA GPUs, taking advantage of the platform's programmability to test and implement improvements. Uday Ruddarraju, chief technology officer of compute at OpenAI, said the companies used OpenAI's internal models to optimize inference on NVIDIA GPUs, and that NVIDIA's programmability helped deliver the acceleration behind Astra Ultrafast.

NVIDIA stated that a programmable platform allows developers and researchers to reuse infrastructure across training, inference and reinforcement learning as models evolve, and that this flexibility helps teams repurpose compute resources as demand changes. Developers can use GPT-6 Astra Ultrafast through the API today, with a guide available for access, pricing and implementation details.