GitHub[208K]試用 OpenCode

CompareAI models

  1. Jamba LargeAi21
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Jamba Large0/100No data25/10052/1000/100No data
Kimi K2.5100/10020/10044/10062/10050/100No data
Overview
Author
Context length
256K
262K
Reasoning
False
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.60/ 1M
Output
$8.00/ 1M
$3.00/ 1M
Cached input
Unknown
$0.10/ 1M
MomentumLast 2 mo
Unique users
No usage
46K
Completed sessions
No usage
13,327
Token share
No usage
0%
Tokens
No usage
28B-80%
No trend data
JUL 25SEP 18
RetentionWeek 1
Returning users
Pending
69.5%763 user-weeks

Related comparisons. Other model pairs to check.