GitHub[195K]Try OpenCode

CompareAI models

  1. test-deepinfraDeepSeek
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
test-deepinfraNo dataNo dataNo dataNo dataNo dataNo data
Kimi K2.5100/10020/10043/10064/10050/100No data
Overview
Author
Context length
Unknown
262K
Reasoning
Unknown
True
Input modalities
Unknown
Text, Image, Video
Output modalities
Unknown
Text
Providers
Pricing
Input
Unknown
$0.60/ 1M
Output
Unknown
$3.00/ 1M
Cached input
Unknown
$0.10/ 1M
MomentumLast 2 mo
Unique users
1
62K
Completed sessions
1
2,490
Token share
0%
0.01%
Tokens
35K+100%
45B-87%
JUL 3AUG 27
JUL 3AUG 27
RetentionWeek 1
Returning users
Pending
72.9%929 user-weeks

Related comparisons. Other model pairs to check.