Claude Opus 5.5 vs Mercury 2
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mercury 2 is 21.3× cheaper than Claude Opus 5.5 on a typical 3:1 input/output mix. Claude Opus 5.5 has the larger context window (1M vs 128K).
| Claude Opus 5.5 | Mercury 2 | |
|---|---|---|
| Input price / 1M | $4.00 | $0.25 |
| Output price / 1M | $20.00 | $0.75 |
| Blended price (3:1) | $8.00 | $0.38 |
| Cached input / 1M | $0.20 | $0.025 |
| Context window | 1M | 128K |
| Max output | 128K | 50K |
| Intelligence index | 57.6 | — |
| Coding index | — | 31.1 |
| Providers | 11 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-09-22 | 2026-03-04 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Claude Opus 5.5 or Mercury 2?
Mercury 2 is 21.3× cheaper than Claude Opus 5.5 on a typical 3:1 input/output mix.
Claude Opus 5.5 vs Mercury 2: which has a bigger context window?
Claude Opus 5.5: 1,000,000 tokens. Mercury 2: 128,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Claude Opus 5.5 ≈ $18,000, Mercury 2 ≈ $875.00.
More comparisons
Claude Opus 5.5 vs GLM 5.3 PrimeClaude Opus 5.5 vs Qwen3.8 Max PrimeClaude Opus 5.5 vs Command A+Claude Opus 5.5 vs GPT-6 Luna ProClaude Opus 5.5 vs GPT-6 LunaClaude Opus 5.5 vs GPT-6 Sol ProClaude Opus 5.5 vs GPT-6 SolClaude Opus 5.5 vs MiMo-V2.6-Pro-UltraSpeedClaude Opus 5.5 vs MiMo-V2.6-FlashClaude Opus 5.5 vs Grok 4.7Claude Opus 5.5 vs Qwen3.8 Omni FlashClaude Opus 5.5 vs GLM 5.3 FlashXClaude Opus 5.5 vs DeepSeek V4.1 FlashClaude Opus 5.5 vs GPT-6 AstraClaude Opus 5.5 vs GPT-6 Astra ProClaude Opus 5.5 vs Qwen3.8 Max (0902)Mercury 2 vs GLM 5.3 PrimeMercury 2 vs Qwen3.8 Max PrimeMercury 2 vs Command A+Mercury 2 vs GPT-6 Luna ProMercury 2 vs GPT-6 LunaMercury 2 vs GPT-6 Sol ProMercury 2 vs GPT-6 SolMercury 2 vs MiMo-V2.6-Pro-UltraSpeed