{"slug": "openai-ultrafast-mode-now-available-on-ai-gateway", "title": "OpenAI Ultrafast mode now available on AI Gateway", "summary": "Vercel's AI Gateway now supports OpenAI's Ultrafast service tier for GPT-6 Astra, giving developers faster output for interactive applications and rapid coding iterations. Ultrafast requests are billed at 6× the standard per-token rate, and requests pinned to unsupported regions such as the EU fall back to the standard default tier, which remains the default when no service tier is specified. OpenAI recommends the Responses API over a persistent WebSocket connection for workflows with frequent tool calls to reduce overhead between turns.", "body_md": "[AI Gateway](https://vercel.com/ai-gateway) now supports OpenAI's Ultrafast service tier for GPT-6 Astra, providing faster output for interactive applications and rapid coding iterations.\n\nTo use Ultrafast, request it for `openai/gpt-6-astra` through AI SDK, the Chat Completions API, or Responses API:\n\nFor workflows with frequent tool calls, OpenAI recommends the Responses API over a persistent WebSocket connection to reduce overhead between turns. See the [Ultrafast service-tier examples](https://vercel.com/docs/ai-gateway/models-and-providers/service-tiers#ultrafast) for persistent connections, including AI SDK over WebSocket.\n\nUltrafast supports US and global processing. Requests pinned to unsupported regions, such as the EU, run at the standard (`default`) tier. Standard processing remains the default when no service tier is specified.\n\nRequests served at Ultrafast are billed at 6× the standard per-token rate, while requests that fall back to another tier are billed at the rate for the tier actually served. Check the [GPT-6 Astra model page](https://vercel.com/ai-gateway/models/gpt-6-astra) for current rates.", "url": "https://wpnews.pro/news/openai-ultrafast-mode-now-available-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/openai-ultrafast-mode-now-available-on-ai-gateway", "published_at": "2026-10-05 00:00:00+00:00", "updated_at": "2026-10-07 21:16:06.215898+00:00", "lang": "en", "topics": ["ai-infrastructure", "large-language-models", "ai-products", "developer-tools"], "entities": ["OpenAI", "Vercel", "AI Gateway", "GPT-6 Astra", "AI SDK", "Chat Completions API", "Responses API"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openai-ultrafast-mode-now-available-on-ai-gateway", "markdown": "https://wpnews.pro/news/openai-ultrafast-mode-now-available-on-ai-gateway.md", "text": "https://wpnews.pro/news/openai-ultrafast-mode-now-available-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/openai-ultrafast-mode-now-available-on-ai-gateway.jsonld"}}