Hermes 4 70 B vs Hy 3: cost comparison
Prices updated 2026-10-27 · computed from live provider data
Short answer: Hermes 4 70 B is cheaper on a
3:1 input/output blend — $0.198 per million tokens versus
$0.231, a 15% difference.
Hy 3 offers the larger context window at 262,144 tokens, against 131,072 for Hermes 4 70 B.
Head to head
| Hermes 4 70 B | Hy 3 | |
|---|---|---|
| Input, per 1M tokens | $0.130 | $0.132 |
| Output, per 1M tokens | $0.400 | $0.528 |
| Blended 3:1, per 1M | $0.198 | $0.231 |
| Context window | 131,072 | 262,144 |
| Vendor | nebius | tencent |
Monthly cost at real volumes
| Workload (input / output) | Hermes 4 70 B | Hy 3 |
|---|---|---|
| 1M in / 250K out | $0.230 | $0.264 |
| 10M in / 2.5M out | $2.30 | $2.64 |
| 100M in / 25M out | $23.00 | $26.40 |
Which should you pick?
Pick Hy 3 when you need the longer context window (262,144 vs 131,072 tokens). Pick Hermes 4 70 B when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.