GPT-5.1 Codex Mini vs Mercury 2: cost comparison
Prices updated 2026-11-09 · computed from live provider data
Short answer: Mercury 2 is cheaper on a
3:1 input/output blend — $0.375 per million tokens versus
$0.688, a 45% difference.
GPT-5.1 Codex Mini offers the larger context window at 400,000 tokens, against 128,000 for Mercury 2.
Head to head
| GPT-5.1 Codex Mini | Mercury 2 | |
|---|---|---|
| Input, per 1M tokens | $0.250 | $0.250 |
| Output, per 1M tokens | $2.00 | $0.750 |
| Blended 3:1, per 1M | $0.688 | $0.375 |
| Context window | 400,000 | 128,000 |
| Vendor | gpt | inception |
Monthly cost at real volumes
| Workload (input / output) | GPT-5.1 Codex Mini | Mercury 2 |
|---|---|---|
| 1M in / 250K out | $0.750 | $0.438 |
| 10M in / 2.5M out | $7.50 | $4.38 |
| 100M in / 25M out | $75.00 | $43.75 |
Which should you pick?
Pick GPT-5.1 Codex Mini when you need the longer context window (400,000 vs 128,000 tokens). Pick Mercury 2 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.