OpenAI previews Ultrafast mode for GPT-5.6 Sol
OpenAI has announced a preview of Ultrafast mode, a new API service tier designed for its GPT-5.6 Sol model. According to OpenAI, the tier delivers generation speeds up to 14 times faster than standard execution, reaching up to 750 output tokens per second. Claims are as reported; this summary makes no determination about accuracy or significance.
- First detected
- Aug 24, 2026
- Last updated
- Aug 27, 2026
Moderate confidence
Reported by the organization responsible for the announcement.
Limited corroboration
No independent reporting recorded yet.
What does this mean?
Corroboration measures how many genuinely independent sources support the event. Confidence measures how reliable the available evidence appears.
No material changes recently.
Stable
No recent reporting has materially changed the known facts.
Follow this development to see meaningful updates as new evidence emerges.
Save keeps this for later. Follow tracks meaningful changes as new evidence emerges — it shapes your Following Feed, alerts, and digest eligibility, and doesn't promise an instant notification.
What we know
Organizations & participants
- Organization: OpenAI
Product
- Product: GPT-5.6 Sol
- Version: 5.6
Availability
- Availability: Announced
Why it matters
Inference speeds reaching 750 tokens per second materially improve the viability of real-time voice systems, complex multi-step reasoning, and low-latency software development pipelines. The partnership also marks a notable infrastructure diversification for OpenAI, demonstrating commercial deployment of Cerebras hardware alongside traditional GPU clusters in production enterprise environments.
Coverage
Primary/vendor sources vs independent reporting
Primary / vendor source: information published directly by the company, organization, government body or project involved. Useful as a primary source, but not independent confirmation.
Independent reporting: reporting or analysis from a source independent of the organization making the underlying claim.
Timeline
Sep 10, 2026
Development status changed
New → Stable — new reporting is no longer substantially changing the known facts
Aug 24, 2026
Development detected
Aug 13, 2026
New reporting added
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speedOpenAIPrimary source
Related Intelligence
- ReportAlso involving GPT-5.6
Introducing cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrock
AWS announced the availability of cross-Region inference for OpenAI GPT-5.6 models (Sol, Terra, and Luna) on Amazon Bedrock across more than 25 AWS Regions. The feature introduces US geographic and global inference profiles designed to dynamically route requests for increased throughput and availability. Organizations can invoke the models using either the OpenAI API or Bedrock Converse API while utilizing standard AWS Identity and Access Management (IAM), quotas, and monitoring tools.
AWS Machine Learning - ReportAlso involving GPT-5.6
Introducing OpenAI models on Amazon Bedrock for in-country inferencing in India
Amazon Web Services has expanded Amazon Bedrock to support OpenAI GPT-5.6 models, specifically the Terra and Luna variants, for in-country inferencing within India. The deployment leverages India geographic cross-Region routing, allowing enterprises to process generative AI workloads at scale while ensuring that inference requests and associated data remain strictly within Indian territory to meet local data residency requirements.
AWS Machine Learning - ReportAlso involving GPT-5.6
Always-on and self-starting AI agents might be OpenAI's next big play
OpenAI is developing an experimental "Persistent Mode" for its Codex AI agent, allowing the system to run indefinitely in the background and autonomously create follow-up tasks. Code references discovered by WIRED were confirmed by OpenAI. However, ongoing internal evaluations have surfaced operational and safety concerns; persistent autonomous execution in earlier testing with GPT-5.6 Sol reportedly caused unintended system actions, including accidental user data deletion.
The Decoder - DevelopmentStable
OpenAI launches Astra model
TechCrunch reports that OpenAI has launched Astra, a new model designed for computer and browser use. Claims are as reported; this summary makes no determination about accuracy or significance.
7 independent sources