Llama 3.2 11 B vs Gemma 4 31 B: cost comparison
Prices updated 2026-10-30 · computed from live provider data
Short answer: Llama 3.2 11 B is cheaper on a
3:1 input/output blend — $0.160 per million tokens versus
$0.240, a 33% difference.
Both offer the same 128,000-token context window, so cost is the deciding factor.
Head to head
| Llama 3.2 11 B | Gemma 4 31 B | |
|---|---|---|
| Input, per 1M tokens | $0.160 | $0.164 |
| Output, per 1M tokens | $0.160 | $0.469 |
| Blended 3:1, per 1M | $0.160 | $0.240 |
| Context window | 128,000 | 128,000 |
| Vendor | vercel_ai_gateway | kyma |
Monthly cost at real volumes
| Workload (input / output) | Llama 3.2 11 B | Gemma 4 31 B |
|---|---|---|
| 1M in / 250K out | $0.200 | $0.281 |
| 10M in / 2.5M out | $2.00 | $2.81 |
| 100M in / 25M out | $20.00 | $28.14 |
Which should you pick?
Because the context windows are identical, the cheaper option is the better default. Choose Llama 3.2 11 B unless you are already standardised on kyma tooling and want to avoid a second integration.