OpenCode 사용해 보기지금 써보기

Compare AI models: Kimi K3 vs Hy3

  1. Kimi K3MoonshotHollow points use fallbacks · hover for details
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K3100/100100/10013/10092/10050/10050/100 — Tool calling supported; no comparable benchmark
Hy367/10070/10080/10052/1000/10040/100
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$2.55/ 1M
$0.07/ 1M
Output
$13/ 1M
$0.26/ 1M
Cached input
$0.26/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
192K
55K
Completed sessions
624,369
394,997
Token share
0.03%
0.01%
Tokens
431B-69%
140B-98%
SEP 21NOV 15
SEP 21NOV 15
RetentionWeek 1
Returning users
41.3%12K user-weeks
64.1%1.1K user-weeks

Related comparisons. Other model pairs to check.