GPT-6.2 Ultrafast in Codex: Up to 4.5x Faster Tokens, Dev Says It Restores Flow

dkundel · x · 2026-11-21

Developer dkundel shares how GPT-6.2 Astra/Sol's new Ultrafast mode (up to 4.5x faster token generation in Codex) changes his workflow: Sol Ultrafast ships on the $200 Pro plan, with an API promo at 3x Standard pricing instead of 6x.

Original post →

More from coding & agent

coding & agent channel →