Skip to main content
← back to home

// changelog

What changed.
Without the marketing voice.

Versioned. Dated. Terse. If a release affects pricing, retention, or anything legally meaningful, it's also flagged in privacy or terms with a separate notice.

RSS

v22026-08-01New model, faster boxes, tighter limits
  • New coding model on the fleet — stronger tool-calling and reasoning, and it holds a plan across many steps instead of stopping halfway. Runs with full-precision KV cache, which fixed the multi-turn edit failures some users hit.
  • Much faster responses, and no more waiting behind other sessions at busy times.
  • Long answers no longer run away — they finish in minutes, and a cut-off reply now tells you why instead of stopping silently.
  • Context window stated honestly at 200K, the model's real ceiling.
  • Clearer plan limits, with a per-session allowance that scales across the Lite tiers.
  • Windows setup smoothed out — fewer failed commands, clearer install docs.
v12026-05-05Initial release
  • Custom-tuned coding model on dedicated GPU infrastructure — no foundation-lab content policy upstream.
  • CLI client with verification gate, read-before-overwrite, and loop / failed-path guards.
  • Lite: a $20 2-day trial. Monthly tiers: Pro $250/mo, Pro+ $350/mo, Enterprise $1000/mo. 1/3/12-month prepaid periods (annual saves 20%).
  • Crypto-only billing — USDT TRC20/ERC20, BTC, ETH. No card on file, no recurring charges.
  • Dashboard: usage analytics, plan status, billing checkout, account management.
  • Privacy: no training on customer prompts, 24-hour auto-purge of inactive sessions.