Qwen 3.6 35 B A3 B vs Mercury 3: cost comparison
Prices updated 2026-10-27 · computed from live provider data
Short answer: Mercury 3 is cheaper on a
3:1 input/output blend — $0.163 per million tokens versus
$0.312, a 48% difference.
Mercury 3 offers the larger context window at 1,000,000 tokens, against 262,144 for Qwen 3.6 35 B A3 B.
Head to head
| Qwen 3.6 35 B A3 B | Mercury 3 | |
|---|---|---|
| Input, per 1M tokens | $0.100 | $0.100 |
| Output, per 1M tokens | $0.950 | $0.350 |
| Blended 3:1, per 1M | $0.312 | $0.163 |
| Context window | 262,144 | 1,000,000 |
| Vendor | qwen | inception |
Monthly cost at real volumes
| Workload (input / output) | Qwen 3.6 35 B A3 B | Mercury 3 |
|---|---|---|
| 1M in / 250K out | $0.338 | $0.188 |
| 10M in / 2.5M out | $3.38 | $1.88 |
| 100M in / 25M out | $33.75 | $18.75 |
Which should you pick?
Pick Mercury 3 when you need the longer context window (1,000,000 vs 262,144 tokens). Pick Mercury 3 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.