DeepSeek V3 (March 2024) vs Kimi K2.7 Code
Compare DeepSeek V3 (March 2024) by DeepSeek against Kimi K2.7 Code by Moonshot AI, context windows of 128K vs 262K, tested across 54 shared challenges.
Our Verdict
DeepSeek V3 (March 2024)
Kimi K2.7 Code
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
DeepSeek V3 (March 2024) is 14x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
DeepSeek V3 (March 2024)
Input
$0.14
6.8× cheaper
Output
$0.28
14× cheaper
Kimi K2.7 Code
Input
$0.95
Output
$4.00
DeepSeek V3 (March 2024) is cheaper on both — 6.8× input, 14× output
Writing DNA
Style Comparison
Similarity
44%
DeepSeek V3 (March 2024) uses 25.6x more emoji
DeepSeek V3 (March 2024)
Kimi K2.7 Code
58%Vocabulary57%
18wSentence Length19w
0.73Hedging0.51
7.5Bold4.7
7.6Lists3.3
0.26Emoji0.00
1.60Headings0.76
0.08Transitions0.05
Based on 16 + 27 text responses
Research
What we learned reading every model
FAQ
