Your sovereign, private Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's proprietary successor to Kimi K3: a 2.8T-parameter model with a 1M-token context window, native image input and extended reasoning. It scores 46 on the Artificial Analysis Intelligence Index (up from 29 for the released K3 build) and leads on long-horizon agentic work. Note the trade-off: output speed is roughly 31 tokens per second on the standard endpoint, so prefer the High-speed variant for interactive use. A reasoning model in the ultra tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in US dollars per million tokens at the published rates below. No training on your data, no vendor lock-in.
How Kimi K3.1 Pro compares
Independent intelligence index for Kimi K3.1 Pro against every peer in the Ultra tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Run Kimi K3.1 Pro privately
One key, one endpoint, three jurisdictions.
- Size tierUltra
- Serving routeStandard
- Input rate$4.20/1M
- Output rate$21.00/1M
- Cached input rate$0.42/1M
- Context window1000K tokens
- Max output32K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputSupports image input
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call