Sovereign inference — Kimi K3.1 Pro High Speed
Your sovereign, private Kimi K3.1 Pro High Speed
Kimi K3.1 Pro served on Novita's high-speed endpoint: the same 2.8T-parameter proprietary model and 1M-token context as the standard variant, at roughly 74 tokens per second (about 2.4x faster) for a higher per-token price. Use this variant when interactive latency matters more than cost. A reasoning model in the ultra tier on the priority serving route, 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.
AU · EU · US resident$6.30/1M input$31.50/1M output$0.32/1M cached input1000K contextPriority serving
How Kimi K3.1 Pro High Speed compares
Independent intelligence index for Kimi K3.1 Pro High Speed 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 High Speed privately
One key, one endpoint, three jurisdictions.
- Size tierUltra
- Serving routePriority
- Input rate$6.30/1M
- Output rate$31.50/1M
- Cached input rate$0.32/1M
- 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