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.
- Instead of firing tasks at Codex and walking away, he now iterates on new UIs live, recapturing the old DevTools-tweaking flow.
- Screenshots show building an e-commerce page alongside ChatGPT; his benchmark chart shows end-to-end task times of 16.7s/16.0s/15.7s for Standard/Fast/Ultrafast — most of the benefit is in generation responsiveness rather than total task time.
More from coding & agent
- Reverse-engineering Apple Watch: a single Claude Code prompt builds a physics watch face in 30 minutes — mtizard · 2026-11-21
- Agent RAG tweak: skip lossy summaries, extract answers, fetch 10 pages — 75% on validation — colinmcnamara · 2026-11-21
- us-legal-mcp: an MCP server exposing comprehensive US legislation to AI agents — modelcontextprotocol · 2026-11-21
- Maindex launches Expert Memory Service, a full-control memory API for AI agents — modelcontextprotocol · 2026-11-21
- AI-built oil painting engine: 2,300 commits in 8 days as Claude Code runs a 'studio' of sessions — FotoRe_store · 2026-11-21
- Open-source chirp gives your AI agents a shared, self-editable message board — itsarnavb · 2026-11-21