GitHub[220K]Try OpenCode

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 K3100/100100/10010/10092/10050/10050/100 — Tool calling supported; no comparable benchmark
Hy367/10068/10071/10053/1000/10040/100
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$3.00/ 1M
$0.13/ 1M
Output
$15/ 1M
$0.53/ 1M
Cached input
$0.30/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
228K
65K
Completed sessions
746,312
463,299
Token share
0.04%
0.02%
Tokens
522B-71%
222B-97%
SEP 5OCT 30
SEP 5OCT 30
RetentionWeek 1
Returning users
40.4%18K user-weeks
64%1.9K user-weeks

Related comparisons. Other model pairs to check.