Inkling Small vs Qwen 2.5 72 B Instruct: cost comparison
Prices updated 2026-11-07 · computed from live provider data
Short answer: Qwen 2.5 72 B Instruct is cheaper on a
3:1 input/output blend — $0.370 per million tokens versus
$0.510, a 27% difference.
Inkling Small offers the larger context window at 524,288 tokens, against 32,768 for Qwen 2.5 72 B Instruct.
Head to head
| Inkling Small | Qwen 2.5 72 B Instruct | |
|---|---|---|
| Input, per 1M tokens | $0.360 | $0.360 |
| Output, per 1M tokens | $0.960 | $0.400 |
| Blended 3:1, per 1M | $0.510 | $0.370 |
| Context window | 524,288 | 32,768 |
| Vendor | thinkingmachines | qwen |
Monthly cost at real volumes
| Workload (input / output) | Inkling Small | Qwen 2.5 72 B Instruct |
|---|---|---|
| 1M in / 250K out | $0.600 | $0.460 |
| 10M in / 2.5M out | $6.00 | $4.60 |
| 100M in / 25M out | $60.00 | $46.00 |
Which should you pick?
Pick Inkling Small when you need the longer context window (524,288 vs 32,768 tokens). Pick Qwen 2.5 72 B Instruct when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.