Back to Newsroom
Short News

OpenAI introduces 'Ultrafast,' a new mode that makes GPT-5.6 Sol work at 14x the speed

By Modelverse Editorial·August 13, 2026·2 min read
OpenAI introduces 'Ultrafast,' a new mode that makes GPT-5.6 Sol work at 14x the speed

Introduction of Ultrafast Mode

OpenAI has introduced Ultrafast, a new mode designed to accelerate the processing speed of its GPT-5.6 Sol model. This mode operates at 14 times the standard processing speed, delivering up to 750 output tokens per second. Ultrafast achieves real-time speed without requiring a smaller or more specialized model, indicating progress toward increased work output per second.

Key Specifications and Applications

Ultrafast's specifications and applications include:

  • Processing speed of up to 750 output tokens per second.
  • Deployment suitability across corporate workflows such as incident response, customer service, financial market analysis, and e-commerce.
  • Powered by a partnership between OpenAI and chipmaker Cerebras. The mode is currently in preview, with access limited to a small group of customers. OpenAI plans to expand access as capacity grows.

Competitive Landscape

OpenAI's competitors, such as Anthropic, have also launched accelerated model versions, including Claude's fast mode. However, Claude's fast mode does not deliver the speed offered by Ultrafast.

ai-newsbreakingtechcrunch-ai

Footnotes & Primary References

Related content

Writer introduces new AI model and upgraded harness to contain token costs

Built as a post-training variation on Z.ai's open source model GLM-5.2, Writer says the new system should provide deployment-ready capabilities at a much lower price.

Read article

Nvidia's new $500B plan is risky but brilliant, especially for aging GPUs

Nvidia has a plan to make sure its GPUs won't lose value. It wants to convince a new crop of financiers to keep lending for AI buildouts.

Read article

Xiaomi's MiLM Plus Releases PROVE: Perception-Aligned Object Removal Metrics RC-S and RC-T With a Real-World Video Benchmark

Object removal models have improved faster than the metrics used to judge them. Diffusion erasers now reconstruct shadows, reflections and occluded structure convincingly, yet PSNR...

Read article