Command A+ vs Mercury 2.5
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mercury 2.5 is 8.9× cheaper than Command A+ on a typical 3:1 input/output mix. Mercury 2.5 has the larger context window (260K vs 192K).
| Command A+ | Mercury 2.5 | |
|---|---|---|
| Input price / 1M | $0.30 | $0.04 |
| Output price / 1M | $1.50 | $0.15 |
| Blended price (3:1) | $0.60 | $0.0675 |
| Cached input / 1M | $0.15 | $0.004 |
| Context window | 192K | 260K |
| Max output | 64K | 66K |
| Intelligence index | — | — |
| Coding index | — | — |
| Providers | 1 | — |
| Best provider uptime (30m) | — | — |
| Vision input | Yes | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-09-22 | 2026-09-08 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Command A+ or Mercury 2.5?
Mercury 2.5 is 8.9× cheaper than Command A+ on a typical 3:1 input/output mix.
Command A+ vs Mercury 2.5: which has a bigger context window?
Command A+: 192,000 tokens. Mercury 2.5: 260,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Command A+ ≈ $1,350, Mercury 2.5 ≈ $155.00.
More comparisons
Command A+ vs GLM 5.3 PrimeCommand A+ vs Qwen3.8 Max PrimeCommand A+ vs GPT-6 Luna ProCommand A+ vs GPT-6 LunaCommand A+ vs GPT-6 Sol ProCommand A+ vs GPT-6 SolCommand A+ vs Claude Opus 5.5Command A+ vs MiMo-V2.6-Pro-UltraSpeedCommand A+ vs MiMo-V2.6-FlashCommand A+ vs Grok 4.7Command A+ vs Qwen3.8 Omni FlashCommand A+ vs GLM 5.3 FlashXCommand A+ vs DeepSeek V4.1 FlashCommand A+ vs GPT-6 AstraCommand A+ vs GPT-6 Astra ProCommand A+ vs Qwen3.8 Max (0902)Mercury 2.5 vs GLM 5.3 PrimeMercury 2.5 vs Qwen3.8 Max PrimeMercury 2.5 vs GPT-6 Luna ProMercury 2.5 vs GPT-6 LunaMercury 2.5 vs GPT-6 Sol ProMercury 2.5 vs GPT-6 SolMercury 2.5 vs Claude Opus 5.5Mercury 2.5 vs MiMo-V2.6-Pro-UltraSpeed