DeepSeek V3.1vsMercury
DeepSeek V3.1 is cheaper than Mercury at $0.2/M vs $10/M input tokens.
| Spec | DeepSeek V3.1 | Mercury |
|---|---|---|
| Input price | $0.2/M tokens | $10/M tokens |
| Output price | $0.8/M tokens | $10/M tokens |
| Context window | 164K tokens | 32K tokens |
| Released | Aug 2025 | Jun 2025 |
Our Verdict
DeepSeek V3.1
MercuryRunner-up
Not enough votes to call it. On the specs, DeepSeek V3.1 has the edge: bigger model tier, newer, bigger context window, major provider backing.
DeepSeek V3.1 costs 13x less per token.
Slight edge
API pricing
Cost per 1M tokens
DeepSeek V3.1
Input
$0.20
50× cheaper
Output
$0.80
13× cheaper
Mercury
Input
$10.00
Output
$10.00
DeepSeek V3.1 is cheaper on both — 50× input, 13× output
Writing DNA
Style Comparison
Similarity
30%
DeepSeek V3.1 uses 6.6x more transitions
DeepSeek V3.1
Mercury
53%Vocabulary55%
14wSentence Length40w
0.42Hedging0.39
4.0Bold4.9
3.6Lists3.8
0.02Emoji0.04
0.40Headings1.04
0.22Transitions0.03
Based on 23 + 17 text responses
Research
What we learned reading every model
FAQ
