OpenAI Codex Mini vs Kimi Linear 48B A3B Instruct
Compare OpenAI Codex Mini by OpenAI against Kimi Linear 48B A3B Instruct by Moonshot AI, context windows of 200K vs 1.0M, tested across 9 shared challenges.
Our Verdict
Kimi Linear 48B A3B Instruct
OpenAI Codex MiniRunner-up
No community votes yet. On paper, Kimi Linear 48B A3B Instruct has the edge — bigger model tier, newer, bigger context window.
Kimi Linear 48B A3B Instruct is 10x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
OpenAI Codex Mini
Input
$1.50
Output
$6.00
Kimi Linear 48B A3B Instruct
Input
$0.30
5.0× cheaper
Output
$0.60
10× cheaper
Kimi Linear 48B A3B Instruct is cheaper on both — 5.0× input, 10× output
Research
What we learned reading every model
FAQ
