GLM 4.6vsMercury
GLM 4.6 is cheaper than Mercury at $0.4/M vs $10/M input tokens.
| Spec | GLM 4.6 | Mercury |
|---|---|---|
| Input price | $0.4/M tokens | $10/M tokens |
| Output price | $1.75/M tokens | $10/M tokens |
| Context window | 203K tokens | 32K tokens |
| Weights | Open | — |
| Free API (OpenRouter) | No | No |
| Released | Sep 2025 | Jun 2025 |
Our Verdict
GLM 4.6
MercuryRunner-up
Not enough votes to call it. On the specs, GLM 4.6 has the edge: bigger model tier, newer, bigger context window, major provider backing.
GLM 4.6 wins Image Generation and Web Design. GLM 4.6 costs 5.7x less per token.
Slight edge
API pricing
Cost per 1M tokens
GLM 4.6
Input
$0.40
25× cheaper
Output
$1.75
5.7× cheaper
Mercury
Input
$10.00
Output
$10.00
GLM 4.6 is cheaper on both: 25× input, 5.7× output.
Where to run it
5 hosts, cheapest first
Mercury
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Writing DNA
Style Comparison
Similarity
34%
GLM 4.6 uses 5.1x more emoji
GLM 4.6
Mercury
52%Vocabulary60%
16wSentence Length31w
0.31Hedging0.78
5.1Bold4.1
3.2Lists2.8
0.14Emoji0.03
0.54Headings0.88
0.08Transitions0.06
Based on 28 + 26 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
