Meta: Llama 3.1 8B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Everything else
| Max output | 131K |
|---|---|
| Input / 1M | $0.05 |
| Output / 1M | $0.08 |
| Cache read / 1M | $0.025 |
| Cache write / 1M | — |
| 1M in + 1M out | $0.13 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | yes |
| Released | 2024-07-23 |
| Knowledge cutoff | 2023-12-31 |
| Retires | — |
| Catalog id | meta-llama/llama-3.1-8b-instruct |
Benchmarks
| source | epoch |
|---|---|
| gpqa | 0.259 |
| gpqaStderr | 0.0167 |
| mathLevel5 | 0.229 |
| mathLevel5Stderr | 0.0085 |
| aime | 0.025 |
| aimeStderr | 0.0223 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.