Ultrafast
Named by 3 kept items in this workspace.
Search every workspace for Ultrafast. It matches the name as written, so it can find other things that share it.
The items that name it 3
Faster generation mode offering up to 8x speed (300 tok/s) in Codex and 6x in the API, at 6x pricing
OpenAI's premium speed tier that generates tokens up to 8x faster in Codex (300 tokens per second) and up to 6x faster in the API, at up to 6x the price of normal usage; has run on Cerebras chips since OpenAI's August preview
Fast inference tier, up to 8x faster (up to 300 tokens/second) at 6x the standard price, available in the API, ChatGPT and Codex; used to power live 3D modeling and app-building demos and cited as enabling the ChatGPT/Codex desktop app merge in 28 days.
All technologies in this workspace.