Private AI
Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.
Added Jun 15, 2026
Context Window
262.1K
Max Output
65.5K
Input Price (Auto)
$1.90/1M
Output Price (Auto)
$8.00/1M
Cache Read (Auto)
$0.32/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
41.9
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
60.8
GPQA Diamond
Graduate-level scientific reasoning
89.6%
Better than 92% of models compared
HLE
Humanity's Last Exam
32.8%
Better than 91% of models compared
IFBench
Instruction-following benchmark
63.1%
Better than 74% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
90.1%
Better than 84% of models compared
AA-LCR
Long context reasoning evaluation
66.3%
Better than 84% of models compared
SciCode
Python programming for scientific computing
47.5%
Better than 89% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
44.7%
Last updated Aug 4, 2026
Artificial AnalysisBetter than 92% of models compared
