OpenAI previews GPT-5.6 Sol Ultrafast, reaching up to 750 tokens per second and 14X faster processing through Cerebras.
On August 13, 2026, OpenAI and Cerebras Systems unveiled Ultrafast — a new API service tier that runs GPT-5.6 Sol, OpenAI's most capable model, at a vendor-claimed 750 output tokens per second, which ...
Meta's Muse Glimmer is a 30B open-source AI model that runs on a single consumer GPU. It beats larger rivals on agentic ...
Add Decrypt as your preferred source to see more of our stories on Google. Google launched Gemini 3.7 Flash on Thursday, a low-cost coding-and-agents model now generally available. OpenAI previewed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results