Mercury is cheaper than Claude 3 Opus at $10/M vs $15/M input tokens.
| Spec | Claude 3 Opus | Mercury |
|---|---|---|
| Input price | $15/M tokens | $10/M tokens |
| Output price | $75/M tokens | $10/M tokens |
| Context window | 200K tokens | 32K tokens |
| Parameters | Not disclosed | Not disclosed |
| Free API (OpenRouter) | No | No |
| Released | Mar 2024 | Jun 2025 |
| HumanEval | 84.9% | 90.0% |
Not enough votes to call it. On the specs, Claude 3 Opus has the edge: bigger model tier, bigger context window, major provider backing.
Mercury costs 7.5x less per token.
Reviewing agent-written code?See a Brief PR report
Mercury is cheaper on both: 1.5× input, 7.5× output.
Mercury uses 405.9x more bold