Llama 3.1 8B vs Llama 4 Maverick
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
Llama 3.1 8B is 82.7% cheaper on blended cost ($0.065 vs $0.375/Mtok)
|
by Meta
|
Dby DeepInfra
|
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Jul 23, 2024 | Apr 6, 2025 |
| Pricing per million tokens | ||
| Input | $0.050/Mtok | $0.150/Mtok |
| Output | $0.080/Mtok | $0.600/Mtok |
| Blended avg | $0.065/Mtok | $0.375/Mtok |
| Specifications | ||
| Context window | 128K tokens | 1M tokens |
| Parameters | 8B | 17B (128 experts) |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Providers | ||
| Available from |
Meta — $0.050/$0.080/Mtok
|
DeepInfra — $0.150/$0.600/Mtok
|
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Llama 3.1 8B | Llama 4 Maverick | Savings |
|---|---|---|---|
| 1M tokens | $0.07 | $0.38 | $0.31 (82.7%) |
| 10M tokens | $0.65 | $3.75 | $3.1 (82.7%) |
| 100M tokens | $6.5 | $37.5 | $31 (82.7%) |
| 1000M tokens | $65 | $375 | $310 (82.7%) |
Summary
Llama 3.1 8B by Meta costs $0.050/Mtok input and $0.080/Mtok output, with a 128K-token context window. It supports text input.
Llama 4 Maverick by DeepInfra costs $0.150/Mtok input and $0.600/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, Llama 3.1 8B is 82.7% cheaper than Llama 4 Maverick.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.