GPT-6.1 Terra vs Mercury 3
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mercury 3 is 12.3× cheaper than GPT-6.1 Terra on a typical 3:1 input/output mix. GPT-6.1 Terra has the larger context window (1.1M vs 1M).
| GPT-6.1 Terra | Mercury 3 | |
|---|---|---|
| Input price / 1M | $1.00 | $0.10 |
| Output price / 1M | $5.00 | $0.35 |
| Blended price (3:1) | $2.00 | $0.16 |
| Cached input / 1M | $0.05 | $0.01 |
| Context window | 1.1M | 1M |
| Max output | 128K | 131K |
| Intelligence index | 51 | — |
| Coding index | — | — |
| Providers | 4 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-10-26 | 2026-10-16 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, GPT-6.1 Terra or Mercury 3?
Mercury 3 is 12.3× cheaper than GPT-6.1 Terra on a typical 3:1 input/output mix.
GPT-6.1 Terra vs Mercury 3: which has a bigger context window?
GPT-6.1 Terra: 1,050,000 tokens. Mercury 3: 1,000,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: GPT-6.1 Terra ≈ $4,500, Mercury 3 ≈ $375.00.
More comparisons
GPT-6.1 Terra vs GPT-6.1 Terra ProGPT-6.1 Terra vs Kimi K3.1 ProGPT-6.1 Terra vs MiniMax M3.1 FlashGPT-6.1 Terra vs DeepSeek V4.1 Flash 1017GPT-6.1 Terra vs Nemotron 3.5 Super VLGPT-6.1 Terra vs Gemini 4 ArgonGPT-6.1 Terra vs Claude Haiku 5.5GPT-6.1 Terra vs Nano Banana 2.1GPT-6.1 Terra vs Mistral Large 4GPT-6.1 Terra vs GPT-6.1 Sol ProGPT-6.1 Terra vs GPT-6.1 SolGPT-6.1 Terra vs Claude Sonnet 5.5GPT-6.1 Terra vs GLM 5.3 PrimeGPT-6.1 Terra vs Qwen3.8 Max PrimeGPT-6.1 Terra vs Command A+GPT-6.1 Terra vs GPT-6 Luna ProMercury 3 vs GPT-6.1 Terra ProMercury 3 vs Kimi K3.1 ProMercury 3 vs MiniMax M3.1 FlashMercury 3 vs DeepSeek V4.1 Flash 1017Mercury 3 vs Nemotron 3.5 Super VLMercury 3 vs Gemini 4 ArgonMercury 3 vs Claude Haiku 5.5Mercury 3 vs Nano Banana 2.1