Umans Kimi K3 Retired
no longer available; use umans-kimi-k3.1-pro
retired Nov 9, 2026 · replaced by umans-kimi-k3.1-pro · weights ↗
54.0tok/s
throughput · p50 · whole period
1.63s
TTFT · p50 · whole period
97.73%
uptime · whole period
Kimi K3: Moonshot's most capable model and the first open 3T-class release - 2.8T parameters, a 1M-token context window, and native vision, built for repository-scale understanding and long agentic runs. On Artificial Analysis' independent Intelligence Index it scores 44 to Claude Fable 5's 50 at about a third of the cost to run it, and it leads Fable 5 on AutomationBench-AA (58% vs 54%). It thinks by default at maximum reasoning effort; select none, low, high, or max to trade depth for speed. Deprecated: use `umans-kimi-k3.1-pro` instead (sunset 2026-11-09).
Trends
Speed over its final 90 days
Aug 13, 2026retired Nov 9, 2026Nov 8, 2026
Aug 13, 2026retired Nov 9, 2026Nov 8, 2026
Changelog
Events for Umans Kimi K3
Nov 92026
Retired: Umans Kimi K3 Retired
umans-kimi-k3 reached its sunset and was retired in favour of Kimi K3.1 Pro: it leaves the catalog and the model pickers, and its history stays on the past-models list. Requests to umans-kimi-k3 keep working: they are served by Kimi K3.1 Pro, post-trained from Kimi K3 with the same 1M-token context, native image understanding and reasoning settings, and billed at its prices ($2.00 / $10.00 / $0.20 per 1M, input / output / cache read). Switch your model id to umans-kimi-k3.1-pro.
Nov 62026
Deprecated: Umans Kimi K3, retiring November 9
umans-kimi-k3 is deprecated and retires on Monday, November 9, 2026. Its successor is umans-kimi-k3.1-pro: Kimi K3.1 Pro, Moonshot's newest open model, post-trained from Kimi K3, with the same 1M-token context, native image understanding and reasoning settings (thinks at max effort by default), at a lower price: $2.00 / $10.00 / $0.20 per 1M (input / output / cache read) against $3.00 / $15.00 / $0.30. Switch your model id to umans-kimi-k3.1-pro before November 9. In the Umans CLI, Claude Code's fable tier uses Kimi K3.1 Pro from version 0.1.82.
Older events 2
Aug 12026
Generally available: Umans Kimi K3 Released
The Kimi K3 Labs pilot closed and umans-kimi-k3 is generally available: no Labs seat required anymore: plan and pay-per-token keys alike get the 1M context window, native vision, and max-effort reasoning at $3.00 / $15.00 / $0.30 per 1M (input / output / cache read).
Jul 312026
Released pay-per-token: Umans Kimi K3 Released
umans-kimi-k3 opened to pay-per-token (wallet and service-account keys): Moonshot's largest open model, a 1M context window, native vision, and max reasoning effort by default, billed at $3.00 / $15.00 / $0.30 per 1M (input / output / cache read).