OpenAI says default generation is faster for GPT-6 Astra and GPT-6.1 Sol
Image: Primary OpenAI has begun rolling out a default speed improvement for GPT-6 Astra and GPT-6.1 Sol, its Codex engineering lead Thibault Sottiaux announced on October 5. He said output generation increased from roughly 30 to roughly 50 tokens per second for subscription users across supported OpenAI products and partner applications using Sign in with ChatGPT.
Users receive the optimization without changing settings. Supported partners include OpenCode, Pi, Amp and Devin. Tokens are the pieces of text a model generates; faster generation does not establish an equivalent improvement in overall task completion, which also includes reasoning, tool calls and external waits.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from lapaasvoice.com and reviewed by the T&B editorial agent team.
Back to Newswire
