Mistral Small 3.2 24 B Instruct vs Ternary Bonsai 2.9 B: cost comparison
Prices updated 2026-10-28 · computed from live provider data
Short answer: Ternary Bonsai 2.9 B is cheaper on a
3:1 input/output blend — $0.092 per million tokens versus
$0.106, a 13% difference.
Ternary Bonsai 2.9 B offers the larger context window at 262,144 tokens, against 256,000 for Mistral Small 3.2 24 B Instruct.
Head to head
| Mistral Small 3.2 24 B Instruct | Ternary Bonsai 2.9 B | |
|---|---|---|
| Input, per 1M tokens | $0.075 | $0.080 |
| Output, per 1M tokens | $0.200 | $0.130 |
| Blended 3:1, per 1M | $0.106 | $0.092 |
| Context window | 256,000 | 262,144 |
| Vendor | mistralai | prism-ml |
Monthly cost at real volumes
| Workload (input / output) | Mistral Small 3.2 24 B Instruct | Ternary Bonsai 2.9 B |
|---|---|---|
| 1M in / 250K out | $0.125 | $0.113 |
| 10M in / 2.5M out | $1.25 | $1.12 |
| 100M in / 25M out | $12.50 | $11.25 |
Which should you pick?
Pick Ternary Bonsai 2.9 B when you need the longer context window (262,144 vs 256,000 tokens). Pick Ternary Bonsai 2.9 B when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.