GPT-5.1-Codex-MinivsKimi K2
Kimi K2 is cheaper than GPT-5.1-Codex-Mini at $0.57/M vs $1.5/M input tokens.
| Spec | GPT-5.1-Codex-Mini | Kimi K2 |
|---|---|---|
| Input price | $1.5/M tokens | $0.57/M tokens |
| Output price | $6/M tokens | $2.3/M tokens |
| Context window | 400K tokens | — |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Nov 2025 | Jul 2025 |
Our Verdict
GPT-5.1-Codex-Mini
Kimi K2Runner-up
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: newer, bigger context window, major provider backing.
Too close to call
Reviewing agent-written code?See a Brief PR report
API pricing
Cost per 1M tokens
GPT-5.1-Codex-Mini
Input
$1.50
Output
$6.00
Kimi K2
Input
$0.57
2.6× cheaper
Output
$2.30
2.6× cheaper
Kimi K2 is cheaper on both: 2.6× input, 2.6× output.
Where to run it
2 hosts
GPT-5.1-Codex-Mini1 host
Kimi K21 host
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
Writing DNA
Style Comparison
Similarity
76%
Kimi K2 uses 53.8x more emoji
GPT-5.1-Codex-Mini
Kimi K2
68%Vocabulary66%
19wSentence Length19w
0.64Hedging0.34
2.7Bold3.3
2.6Lists3.4
0.00Emoji0.54
0.10Headings0.48
0.06Transitions0.05
Based on 17 + 28 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Kimi K2 vs Ox AlphaNew provider
Kimi K2 vs Claude Opus 4New provider
Kimi K2 vs Claude Opus 4.1New provider
Kimi K2 vs Gemini 2.5 Pro (I/O Edition)New provider
GPT-5.1-Codex-Mini vs MiniMax M2.5New provider
GPT-5.1-Codex-Mini vs MiniMax M2.7New provider
Kimi K2 vs MiniMax M3New provider
Kimi K2 vs Mistral LargeNew provider