GLM 5.3 Prime vs Mercury 2
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mercury 2 is 11.5× cheaper than GLM 5.3 Prime on a typical 3:1 input/output mix. GLM 5.3 Prime has the larger context window (1M vs 128K).
| GLM 5.3 Prime | Mercury 2 | |
|---|---|---|
| Input price / 1M | $2.80 | $0.25 |
| Output price / 1M | $8.80 | $0.75 |
| Blended price (3:1) | $4.30 | $0.38 |
| Cached input / 1M | $0.56 | $0.025 |
| Context window | 1M | 128K |
| Max output | 131K | 50K |
| Intelligence index | — | — |
| Coding index | — | 31.1 |
| Providers | 1 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | No | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-09-23 | 2026-03-04 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, GLM 5.3 Prime or Mercury 2?
Mercury 2 is 11.5× cheaper than GLM 5.3 Prime on a typical 3:1 input/output mix.
GLM 5.3 Prime vs Mercury 2: which has a bigger context window?
GLM 5.3 Prime: 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: GLM 5.3 Prime ≈ $10,000, Mercury 2 ≈ $875.00.
More comparisons
GLM 5.3 Prime vs Qwen3.8 Max PrimeGLM 5.3 Prime vs Command A+GLM 5.3 Prime vs GPT-6 Luna ProGLM 5.3 Prime vs GPT-6 LunaGLM 5.3 Prime vs GPT-6 Sol ProGLM 5.3 Prime vs GPT-6 SolGLM 5.3 Prime vs Claude Opus 5.5GLM 5.3 Prime vs MiMo-V2.6-Pro-UltraSpeedGLM 5.3 Prime vs MiMo-V2.6-FlashGLM 5.3 Prime vs Grok 4.7GLM 5.3 Prime vs Qwen3.8 Omni FlashGLM 5.3 Prime vs GLM 5.3 FlashXGLM 5.3 Prime vs DeepSeek V4.1 FlashGLM 5.3 Prime vs GPT-6 AstraGLM 5.3 Prime vs GPT-6 Astra ProGLM 5.3 Prime vs Qwen3.8 Max (0902)Mercury 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 Claude Opus 5.5Mercury 2 vs MiMo-V2.6-Pro-UltraSpeed