Skip to content

Kimi K2.5

by Moonshot AIRank #168Score 47.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Performance Overview

Score
47.5
Rank
#168
24h Change
+3
7d Change
-10
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
83.330%25.02026-11-06T14:59:28.711Z
Pricing
pricing_tier
97.525%24.42026-11-06T14:59:28.711Z
Context Window
context_window
86.015%12.92026-11-06T14:59:28.711Z
Recency
recency
81.215%12.22026-11-06T14:59:28.711Z
Output Capacity
output_capacity
85.915%12.92026-11-06T14:59:28.711Z

Top Drivers

positive
Capabilities
Supports reasoning, vision, tools, JSON mode, streaming
5/7
positive
Pricing
$2.50/M output tokens
$2.50
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 236K output tokens per request
236K

Capabilities

CapabilitySupported
VisionYes
ReasoningYes
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.50
Output / 1M tokens
$2.50
Context Window
262K
Max Output
236K

Related Models

Related

Kimi K2.5 Tracker - Performance History | LM Market Cap