Model comparison
Llama 3.2 vs Llama 3.1
- Input
- $1.38
- Output
- $1.38
- Context
- 128K
- Released
- 2024-09-25
- Input
- $2.75 / 1M tokens
- Output
- $6.50 / 1M tokens
- Context
- 128K
- Released
- 2024-07-23
Llama 3.2 is cheaper on input tokens ($1.4 vs $2.8 per 1M, 2×).
Specs and pricing side by side
| Spec | Llama 3.2 | Llama 3.1 |
|---|---|---|
| Maker | Meta | Metasame |
| Released | 2024-09-25 | 2024-07-23 |
| Context window | 128K | 128Ksame |
| Max output | Not separately specified (shares the 128K… | Provider-dependent (e.g. ~4K on some hosted… |
| Input price | $1.38 | $2.75 / 1M tokens |
| Output price | $1.38 | $6.50 / 1M tokens |
| Parameters | 1B (1.23B), 3B (3.21B), 11B Vision (10.6B), 90B Vision (88.8B) | 8B, 70B, and 405B (dense) |
| License | Llama 3.2 Community License Agreement | Llama 3.1 Community License (custom commercial) |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision | Text |
| Knowledge cutoff | 2023-12 | December 2023 |
Benchmarks both models report
These two models have no benchmark in common in our registry, so there is no like-for-like score to compare. See each model’s own results: Llama 3.2, Llama 3.1.
Which one should you pick?
Pick Llama 3.2 if…
- Cost matters: input tokens cost 2× less ($1.4 vs $2.8 per 1M).
- You need Vision input, which Llama 3.1 lacks.
- Your use case is: on-device and mobile assistants: summarization, rewriting, and instruction following running locally on the 1B or 3B.
Pick Llama 3.1 if…
- Your use case is: self-hosted and on-prem deployments where data cannot leave the org's infrastructure.
FAQ
Which is better, Llama 3.2 or Llama 3.1?
Llama 3.2 is cheaper on input tokens ($1.4 vs $2.8 per 1M, 2×). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Llama 3.2?
Llama 3.2: $1.38 input, $1.38 output. Llama 3.1: $2.75 / 1M tokens input, $6.50 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Llama 3.2 and Llama 3.1?
Llama 3.2 offers 128K with up to Not separately specified (shares the 128K context budget) output; Llama 3.1 offers 128K with up to Provider-dependent (e.g. ~4K on some hosted endpoints); the 128K window is shared between input and output output.
Is Llama 3.2 newer than Llama 3.1?
Llama 3.2 was released 2024-09-25; Llama 3.1 was released 2024-07-23.