Your sovereign, private Kimi K2.6
Kimi K2.6 is Moonshot AI's open-source native multimodal agentic model (1T total / 32B active parameters, 256K context), advancing long-horizon coding, coding-driven design, proactive autonomous execution and swarm-based orchestration — scaling horizontally to 300 coordinated sub-agents for end-to-end task completion. 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.
How Kimi K2.6 compares
Independent intelligence index for Kimi K2.6 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
Capability indexes
Domain-weighted agentic performance for Kimi K2.6.
Capability index vs extra-large peers
The evaluations behind the index
Independent benchmark results for Kimi K2.6 — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 814.73 | 15.6 min | 42409 |
| GDPval-AA | 1026.09 | 9.3 min | 25296 |
| AutomationBench-AA | 13.0% | 8.5 min | 23221 |
| Terminal-Bench 4.0 | 0.5% | 41.5 min | 112817 |
| SciCode | 51.5% | 3.8 min | 10301 |
| Humanity's Last Exam | 37.5% | 15.8 min | 42968 |
| GDP.pdf | 13.0% | 4.7 min | 12836 |
| CritPt | 8.0% | 67.3 min | 182820 |
| AA-Omniscience | 5.30 | 2.4 min | 6397 |
| AA-LCR (long context) | 81.0% | 1.1 min | 3028 |
Run Kimi K2.6 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$0.31/1M
- Context window262K tokens
- Max output262K 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