Back to Models

Kimi K2 Instruct

Advanced Kimi model with improved reasoning depth and instruction following capabilities

Thinking Mode
Parameters
N/A
Context
128,000 tokens
Released
Jan 21, 2025

Leaderboards

Performance vs. Industry Average

Intelligence

Kimi K2 Instruct is of higher intelligence compared to average (4.1), with an intelligence score of 4.2.

Price

Kimi K2 Instruct is cheaper compared to average ($0.91 per 1M Tokens) with a price of $0.24 per 1M Tokens.

Latency

Kimi K2 Instruct has a higher average latency compared to average (45.24s), with an average latency of 65.02s.

P99 Latency

Kimi K2 Instruct has a higher P99 latency compared to average (172.60s), taking 390.47s to receive the first token at P99 (TTFT).

Context Window

Kimi K2 Instruct has a smaller context window than average (246k tokens), with a context window of 128k tokens.

Kimi K2 Instruct - AutoBench