k
keynews.ai
keynews.ai
ToolsThe story, in brief

Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed

14X faster. OpenAI's new Ultrafast tier hits 750 tokens/sec—powered by Cerebras.

Reporting by OpenAI Blog 1 min brief
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
New tools for building and creating with AI.AI illustration by KeyNews
The KeyNews take

Why it matters

A new API service tier fundamentally changes latency economics for practitioners building real-time AI applications. Speed at scale shifts what's viable in production.

The key facts

6 to know

  1. GPT-5.6 Sol model available in Ultrafast tier

  2. Up to 14X speed improvement over standard tier

  3. 750 output tokens per second throughput

  4. Powered by Cerebras hardware partnership

  5. New API service tier (pricing/availability change)

  6. Published August 2026

Go to the source

OpenAI Blogopenai.com

Publisher excerpt: Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools
Tools

OpenAI, Anthropic cut AI model costs as price-performance race intensifies

50% price cut on GPT-6 Sol and Luna. Anthropic drops Claude Opus 5.5 costs 40%. The frontier labs are now competing on inference efficiency, not raw capability — and it changes the calculus for every enterprise AI budget.

CIOAgents

NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%

44.7% fewer tokens. NVIDIA's SoL-Pi cuts coding-agent costs while keeping 94% of performance—auto-research loops discover the optimizations.

MarkTechPostAgents

Ringg’s AI agents resolve up to 65% of customer calls with OpenAI

65% of customer calls resolved autonomously. Ringg's multilingual voice agents cut costs 90% vs. the previous generation.

OpenAI Blog