Private AI
Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added Apr 21, 2026
Model weightsContext Window
262.1K
Max Output
65.5K
Avg output tokens (7d)
4.2K tokens
Input Price (Auto)
$1.50/1M
Output Price (Auto)
$5.25/1M
Cache Read (Auto)
$0.38/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
42.8
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
47.1
GPQA Diamond
Graduate-level scientific reasoning
91.1%
Better than 97% of models compared
HLE
Humanity's Last Exam
35.9%
Better than 96% of models compared
IFBench
Instruction-following benchmark
76.0%
Better than 94% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
95.9%
Better than 96% of models compared
AA-LCR
Long context reasoning evaluation
69.7%
Better than 93% of models compared
SciCode
Python programming for scientific computing
53.5%
Better than 98% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
43.9%
Last updated Jun 17, 2026
Artificial AnalysisBetter than 92% of models compared
