{"slug": "openai-prepares-to-expand-ultrafast-api-to-more-users", "title": "OpenAI prepares to expand Ultrafast API to more users", "summary": "OpenAI is preparing a wider rollout of its Ultrafast API mode around its DevDay event on September 29, with new references appearing across the OpenAI Platform and API documentation, according to TestingCatalog. The mode, already previewed with GPT-5.6 Sol at up to 750 output tokens per second and up to 14× faster inference than Standard, remains limited to selected customers and is powered by Cerebras. A hidden speed selector in the Responses API Playground would let developers choose between Standard, Fast, and Ultrafast processing, though OpenAI has not confirmed which GPT-6 models will support Ultrafast at launch.", "body_md": "OpenAI appears to be preparing a wider rollout of its Ultrafast API mode around DevDay on September 29, with new references showing up across the OpenAI Platform and API documentation.\n\nTestingCatalog spotted a dedicated speed selector being prepared for the Responses API Playground (currently hidden), where developers could choose between Standard, Fast, and Ultrafast processing. OpenAI has already officially previewed Ultrafast with GPT-5.6 Sol, describing speeds of up to 750 output tokens per second and up to 14× faster inference than Standard. Access remains limited to selected customers, and OpenAI confirmed that the mode is powered by Cerebras.\n\nThe timing makes broader availability during DevDay plausible. OpenAI has since released the GPT-6 family, including [GPT-6 Sol](https://www.testingcatalog.com/openai-launches-faster-cheaper-gpt-6-sol-and-luna/) and [GPT-6 Astra](https://www.testingcatalog.com/openai-launches-gpt-6-astra-across-chatgpt-and-api/), making support for these newer models a key thing to watch. No one has confirmed that every GPT-6 model will support Ultrafast at launch.\n\nFor developers, the main trade-off will likely be economics. Standard, Fast, and Ultrafast could let organizations choose latency based on each workload's value, reserving higher-cost inference for applications where response time directly affects revenue or productivity.\n\nThe feature also fits [OpenAI’s](https://www.testingcatalog.com/tag/openai/) broader infrastructure strategy. The company announced a 750 MW Cerebras partnership earlier this year, with capacity being deployed in stages through 2028. TestingCatalog has separately spotted new [OpenAI Platform onboarding tiers](https://www.testingcatalog.com/devday-new-plans-and-new-platform-for-building-ai-apps/), including an Accelerate option aimed at production workloads. Together, these changes suggest DevDay could focus heavily on API infrastructure, compute tiers, and tools for developers building production AI systems.", "url": "https://wpnews.pro/news/openai-prepares-to-expand-ultrafast-api-to-more-users", "canonical_source": "https://www.testingcatalog.com/openai-prepares-to-expand-ultrafast-api-to-more-users/", "published_at": "2026-09-26 12:24:22+00:00", "updated_at": "2026-09-26 12:30:26.029806+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-infrastructure", "ai-tools"], "entities": ["OpenAI", "Ultrafast API", "TestingCatalog", "GPT-5.6 Sol", "Cerebras", "GPT-6 Sol", "GPT-6 Astra", "Responses API Playground"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openai-prepares-to-expand-ultrafast-api-to-more-users", "markdown": "https://wpnews.pro/news/openai-prepares-to-expand-ultrafast-api-to-more-users.md", "text": "https://wpnews.pro/news/openai-prepares-to-expand-ultrafast-api-to-more-users.txt", "jsonld": "https://wpnews.pro/news/openai-prepares-to-expand-ultrafast-api-to-more-users.jsonld"}}