GPT-5.1-Codex-MinivsMercury 2
Mercury 2 is cheaper than GPT-5.1-Codex-Mini at $0.25/M vs $1.5/M input tokens.
| Spec | GPT-5.1-Codex-Mini | Mercury 2 |
|---|---|---|
| Input price | $1.5/M tokens | $0.25/M tokens |
| Output price | $6/M tokens | $0.75/M tokens |
| Context window | 400K tokens | 128K tokens |
| Weights | Closed | — |
| Free API (OpenRouter) | No | No |
| Released | Nov 2025 | Mar 2026 |
Our Verdict
GPT-5.1-Codex-Mini
Mercury 2Runner-up
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: bigger model tier, bigger context window, major provider backing.
Mercury 2 costs 8.0x less per token.
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
Mercury 2
Input
$0.25
6.0× cheaper
Output
$0.75
8.0× cheaper
Mercury 2 is cheaper on both: 6.0× input, 8.0× output.
Where to run it
2 hosts
GPT-5.1-Codex-Mini1 host
Mercury 21 host
Per million tokens. Prices and uptime via OpenRouter, checked 11 Sep 2026.
Writing DNA
Style Comparison
Similarity
44%
Mercury 2 uses 8.2x more emoji
GPT-5.1-Codex-Mini
Mercury 2
68%Vocabulary53%
19wSentence Length22w
0.64Hedging0.40
2.7Bold6.6
2.6Lists2.6
0.00Emoji0.08
0.10Headings0.87
0.06Transitions0.14
Based on 17 + 23 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Mercury 2 vs Ox AlphaNew provider
Mercury 2 vs MiniMax M3New provider
Mercury 2 vs Claude Opus 4New provider
Mercury 2 vs Claude Opus 4.1New provider
GPT-5.1-Codex-Mini vs Qwen3 MaxNew provider
GPT-5.1-Codex-Mini vs Qwen3 Max ThinkingNew provider
GPT-5.1-Codex-Mini vs Qwen3 Next 80B A3B InstructNew provider
GPT-5.1-Codex-Mini vs Qwen3 Next 80B A3B ThinkingNew provider