Skip to content
AI ConnectPowered by VELENTIS
AI-generated1 min

OpenAI Previews Ultrafast API Tier Powered by Cerebras

OpenAI has introduced a preview of Ultrafast, a new API service tier designed to run the GPT-5.6 Sol model at speeds reaching up to 750 output tokens per second.

This article was AI-generated and published automatically. Context, labelling and all sources at the end of the article.

(KI-generiertes Symbolbild: Gemini / AI Connect)

OpenAI has announced a preview of a new API offering called Ultrafast. According to the company, this setup runs the GPT-5.6 Sol model at significantly increased rates, reaching speeds up to 14 times faster than standard execution. The update targets performance improvements for users accessing the model through the API.

The underlying infrastructure for the service tier is powered by Cerebras hardware. Through this integration, the system achieves throughput figures of up to 750 output tokens per second. OpenAI disclosed the preview details to outline the technical capabilities of the new deployment tier.

What this means for you

The introduction of the Ultrafast tier indicates a focus on low-latency and high-throughput generation for demanding model workloads. Organizations building real-time interactive tools or high-volume workflows on GPT-5.6 Sol could see substantial reductions in response times.

Evidence

Solidly sourced
46/100

  • OpenAI is previewing a new API tier called Ultrafast that runs GPT-5.6 Sol up to 14 times faster.

    single source
    Quote

    „Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster.“

    OpenAI, News

  • The service tier runs on Cerebras infrastructure and generates up to 750 output tokens per second.

    single source
    Quote

    „Powered by Cerebras, it delivers up to 750 output tokens per second.“

    OpenAI, News

Sources

The evidence score is computed, not hand-set: from confidence, the number of sources and the share of verified statements.

Source & transparency

As of: August 13, 2026

AI-generatedAI-generated: produced automatically from vetted sources with technical quality checks (source, quote and figure verification); no human sign-off of each item before publication

Sources
1
Verified statements
0 / 2
Evidence score
46Solidly sourced
Generative AI

Want to put this into practice?

We connect you with suitable AI providers from the DACH region, free of charge and without obligation.

What's next?

What does AI really cost?

Honest price ranges for your project, independent, with nothing to sell you.

See prices

Get your team ready (AI Act)

The EU AI Act requires providers and deployers to take measures supporting AI literacy in the team — not a specific level. Baseline training for your team is in development.

Find the right training

Find the right provider

Describe your project. We connect you with suitable providers at a fair price.

Start the analysis
Back to AI Radar