Sovereign inference — Kimi K2.5 Thinking
Your sovereign, private Kimi K2.5 Thinking
Kimi K2.5 is Moonshot AI's large visual-language agentic model (1T total / 32B active parameters, 256K context) with native vision via MoonViT, interleaved thinking and multi-step tool calling — the Thinking variant emphasizes deep reasoning for long-horizon agentic tasks. A reasoning model in the extra-large 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.
AU · EU · US resident$1.56/1M input$4.68/1M output262K context
How Kimi K2.5 Thinking compares
Independent intelligence index for Kimi K2.5 Thinking against every peer in the Extra-large tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Run Kimi K2.5 Thinking privately
One key, one endpoint, three jurisdictions.
- Size tierExtra-large
- Serving routeStandard
- Input rate$1.56/1M
- Output rate$4.68/1M
- Cached input rate—
- Context window262K tokens
- Max output262K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputText only
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call