ainewsblitz.com

Breaking

OpenAI's GPT-5.6 Sol Hits 750 Tokens per Second on Cerebras, Powering Real-Time 3D Modeling in Blender

  • Foundation Models
  • AI Agents
  • Infra & Chips

OpenAI's new flagship model GPT-5.6 Sol has been demonstrated running at up to 750 tokens per second on Cerebras hardware, generating and building 3D scenes inside Blender in real time. The demonstration, presented without any playback speed adjustment, showed the model driving Blender's Python API through a Model Context Protocol (MCP) connection to construct scenes on the fly.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 6,091 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year