Gemini 2.0 Flash ThinkingvsMercury 2
Gemini 2.0 Flash Thinking has a larger context window than Mercury 2 (500K tokens vs 128K tokens).
| Spec | Gemini 2.0 Flash Thinking | Mercury 2 |
|---|---|---|
| Input price | $0.25/M tokens | $0.25/M tokens |
| Output price | $0.5/M tokens | $0.75/M tokens |
| Context window | 500K tokens | 128K tokens |
| Free API (OpenRouter) | No | No |
| Released | Dec 2024 | Mar 2026 |
Our Verdict
Gemini 2.0 Flash Thinking
Mercury 2Runner-up
Not enough votes to call it. On the specs, Gemini 2.0 Flash Thinking has the edge: bigger model tier, 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
Gemini 2.0 Flash Thinking
Input
$0.25
Output
$0.50
1.5× cheaper
Mercury 2
Input
$0.25
Output
$0.75
Where to run it
1 host
Gemini 2.0 Flash Thinking
No hosts listed on OpenRouter.
Mercury 21 host
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
Writing DNA
Style Comparison
Similarity
37%
Mercury 2 uses 8.2x more emoji
Gemini 2.0 Flash Thinking
Mercury 2
54%Vocabulary53%
15wSentence Length22w
0.64Hedging0.40
3.8Bold6.6
2.4Lists2.6
0.00Emoji0.08
0.03Headings0.87
0.30Transitions0.14
Based on 13 + 23 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Gemini 2.0 Flash Thinking vs Ox AlphaNew provider
Gemini 2.0 Flash Thinking vs MiniMax M3New provider
Gemini 2.0 Flash Thinking vs Claude Sonnet 4New provider
Gemini 2.0 Flash Thinking vs Grok 4New provider
Gemini 2.0 Flash Thinking vs Claude Fable 5.1New provider
Gemini 2.0 Flash Thinking vs Claude Haiku 4.5New provider
Gemini 2.0 Flash Thinking vs Claude Opus 4New provider
Gemini 2.0 Flash Thinking vs Claude Opus 4.1New provider