Skip to content

Kimi K2 0905

by Moonshot AIRank #223Score 52.4

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Performance Overview

Score
52.4
Rank
#223
24h Change
0
7d Change
-63
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
50.020%10.02026-08-08T12:28:33.695Z
Benchmarks
benchmark
50.730%15.22026-08-08T12:28:33.695Z
Pricing
pricing_tier
97.515%14.62026-08-08T12:28:33.695Z
Context Window
context_window
86.010%8.62026-08-08T12:28:33.695Z
Recency
recency
71.315%10.72026-08-08T12:28:33.695Z
Output Capacity
output_capacity
83.110%8.32026-08-08T12:28:33.695Z

Top Drivers

neutral
Benchmarks
positive
Pricing
$2.50/M output tokens
$2.50
positive
Recency
Released over 1 year ago
11mo ago
neutral
Capabilities
Supports tools, JSON mode, streaming
3/7

Capabilities

CapabilitySupported
VisionNo
ReasoningNo
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.60
Output / 1M tokens
$2.50
Context Window
262K
Max Output
100K

Related Models

Related

Kimi K2 0905 Tracker - Performance History | LM Market Cap