OpenAI launches Ultrafast across API, ChatGPT, and Codex
YashasGunderia · x · 2026-09-30
OpenAI has rolled out its Ultrafast tier across the API, ChatGPT, and Codex: roughly 8x faster inference at 300 tokens/s for about 6x the price. It's the first time OpenAI has offered an ultra-low-latency option across its whole product line, targeting latency-sensitive coding and realtime use cases.
Related event: OpenAI Launches Ultrafast Tier: 8x Speed at 6x Price Draws Backlash(17 posts)→