GitHub[208K]Essayer OpenCode

Compare AI models: Kimi K2 Instruct vs Kimi K3

  1. Kimi K2 InstructMoonshotHollow points use fallbacks · hover for details
  2. Kimi K3MoonshotHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2 Instruct0/100 — Reasoning not supported50/100 — No data; neutral placeholder46/10034/1000/10050/100 — Tool calling supported; no comparable benchmark
Kimi K3100/100100/10011/10093/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
131K
1M
Reasoning
False
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.57/ 1M
$3.00/ 1M
Output
$2.30/ 1M
$15/ 1M
Cached input
Unknown
$0.30/ 1M
MomentumLast 2 mo
Unique users
No usage
380K
Completed sessions
No usage
756,043
Token share
No usage
0.09%
Tokens
No usage
839B-35%
No trend data
AUG 15OCT 9
RetentionWeek 1
Returning users
Pending
35.8%47K user-weeks

Related comparisons. Other model pairs to check.