Llama 3.8 B Instruct vs Jamba 1.5: cost comparison
Prices updated 2026-10-28 · computed from live provider data
Short answer: Llama 3.8 B Instruct is cheaper on a
3:1 input/output blend — $0.200 per million tokens versus
$0.250, a 20% difference.
Jamba 1.5 offers the larger context window at 256,000 tokens, against 8,192 for Llama 3.8 B Instruct.
Head to head
| Llama 3.8 B Instruct | Jamba 1.5 | |
|---|---|---|
| Input, per 1M tokens | $0.200 | $0.200 |
| Output, per 1M tokens | $0.200 | $0.400 |
| Blended 3:1, per 1M | $0.200 | $0.250 |
| Context window | 8,192 | 256,000 |
| Vendor | gradient_ai | jamba |
Monthly cost at real volumes
| Workload (input / output) | Llama 3.8 B Instruct | Jamba 1.5 |
|---|---|---|
| 1M in / 250K out | $0.250 | $0.300 |
| 10M in / 2.5M out | $2.50 | $3.00 |
| 100M in / 25M out | $25.00 | $30.00 |
Which should you pick?
Pick Jamba 1.5 when you need the longer context window (256,000 vs 8,192 tokens). Pick Llama 3.8 B Instruct when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.