Skip to content

Kimi K2 Thinking

by Moonshot AIRank #350Score 40.0

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Performance Overview

Score
40.0
Rank
#350
24h Change
0
7d Change
0
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.730%20.02026-09-22T14:24:41.877Z
Pricing
pricing_tier
97.525%24.42026-09-22T14:24:41.877Z
Context Window
context_window
86.015%12.92026-09-22T14:24:41.877Z
Recency
recency
74.515%11.22026-09-22T14:24:41.877Z
Output Capacity
output_capacity
79.815%12.02026-09-22T14:24:41.877Z

Top Drivers

positive
Pricing
$2.50/M output tokens
$2.50
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 98K output tokens per request
98K

Capabilities

CapabilitySupported
VisionNo
ReasoningYes
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.60
Output / 1M tokens
$2.50
Context Window
262K
Max Output
98K

Related Models

Related

Kimi K2 Thinking Tracker - Performance History | LM Market Cap