GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users.

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, faster generation can shorten coding agents’ edit-test-debug cycles, reduce the time spent generating responses between tool calls and make interactive applications feel more responsive.

A faster response matters most when it’s repeated across a workflow: an agent writes code, uses a tool, checks the result and decides what to do next. Ultrafast brings Astra’s capabilities into these time-sensitive loops. NVIDIA AI infrastructure helps OpenAI serve more useful model outputs when developers need it.

“NVIDIA’s deep investment in tooling and documentation has enabled us to make our models exceptionally good at programming Blackwell and Rubin GPUs,” said Philippe Tillet, inference lead at OpenAI. “Astra can turn that knowledge into high-performance kernels that make NVIDIA hardware compelling across the full frontier of latency, throughput and cost. With Astra Ultrafast, that means faster model responses as agents write code, use tools and work through complex tasks.”

Continually Improving Performance

Performance gains don’t stop when a model is deployed. 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. That ongoing work can make model responses faster and deployed infrastructure more productive over time.

“Our work with NVIDIA is helping us make AI faster and more useful,” said Uday Ruddarraju, chief technology officer of compute at OpenAI. “We used our internal models to optimize inference on NVIDIA GPUs, and NVIDIA’s programmability helped us deliver the acceleration behind Astra Ultrafast.”

A programmable NVIDIA platform allows developers and researchers to reuse infrastructure across training, inference and reinforcement learning as models evolve. That flexibility helps teams repurpose compute resources as demand changes, improving utilization and avoiding overprovision for each workload.

Developers can use GPT-6 Astra Ultrafast through the API today. See the Ultrafast guide for access, pricing and implementation details.