Mistral Small 24 B Instruct 2501 vs Llama 3.2.3 B Instruct: cost comparison
Prices updated 2026-10-27 · computed from live provider data
Short answer: Mistral Small 24 B Instruct 2501 is cheaper on a
3:1 input/output blend — $0.058 per million tokens versus
$0.120, a 52% difference.
Llama 3.2.3 B Instruct offers the larger context window at 131,072 tokens, against 32,768 for Mistral Small 24 B Instruct 2501.
Head to head
| Mistral Small 24 B Instruct 2501 | Llama 3.2.3 B Instruct | |
|---|---|---|
| Input, per 1M tokens | $0.050 | $0.050 |
| Output, per 1M tokens | $0.080 | $0.330 |
| Blended 3:1, per 1M | $0.058 | $0.120 |
| Context window | 32,768 | 131,072 |
| Vendor | mistralai | meta-llama |
Monthly cost at real volumes
| Workload (input / output) | Mistral Small 24 B Instruct 2501 | Llama 3.2.3 B Instruct |
|---|---|---|
| 1M in / 250K out | $0.070 | $0.133 |
| 10M in / 2.5M out | $0.700 | $1.32 |
| 100M in / 25M out | $7.00 | $13.25 |
Which should you pick?
Pick Llama 3.2.3 B Instruct when you need the longer context window (131,072 vs 32,768 tokens). Pick Mistral Small 24 B Instruct 2501 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.