GitHub[195K]Try OpenCode

CompareAI models

  1. Kimi K2.5Moonshot
  2. qwen3.8-27b-r1Qwen
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Kimi K2.5100/10020/10043/10064/10050/100No data
qwen3.8-27b-r1No dataNo dataNo dataNo dataNo dataNo data
Overview
Author
Context length
262K
Unknown
Reasoning
True
Unknown
Input modalities
Text, Image, Video
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.60/ 1M
Unknown
Output
$3.00/ 1M
Unknown
Cached input
$0.10/ 1M
Unknown
MomentumLast 2 mo
Unique users
62K
516
Completed sessions
2,524
3,253
Token share
0.01%
0%
Tokens
45B-86%
1.3B+100%
JUL 5AUG 29
JUL 5AUG 29
RetentionWeek 1
Returning users
72.9%929 user-weeks
Pending

Related comparisons. Other model pairs to check.