Try OpenCodeTry OpenCode

Compare AI models: Kimi K2.7 Code vs Kimi K3

  1. Kimi K2.7 CodeMoonshotHollow 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 K2.7 Code50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder37/10063/10050/10050/100 — Tool calling supported; no comparable benchmark
Kimi K3100/100100/10013/10092/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
262K
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.69/ 1M
$2.35/ 1M
Output
$3.29/ 1M
$12/ 1M
Cached input
$0.15/ 1M
$0.23/ 1M
MomentumLast 2 mo
Unique users
153K
201K
Completed sessions
591,362
655,475
Token share
0.09%
0.03%
Tokens
1.3T-29%
458B-70%
SEP 17NOV 11
SEP 17NOV 11
RetentionWeek 1
Returning users
56.5%12K user-weeks
41.3%12K user-weeks

Related comparisons. Other model pairs to check.