Input
$0.05
Output
$0.08
Context
128K
Llama 3.1 8B Instruct costs $0.05 per million input tokens and $0.08 per million output tokens. Cached input is billed at $0.025 per million, 50% less than fresh input.
Specifications
| Lab | Meta |
| Model id | meta-llama/llama-3.1-8b-instruct |
| Input price | $0.05 per million tokens |
| Output price | $0.08 per million tokens |
| Cached input price | $0.025 per million tokens |
| Context window | 131,072 tokens (128K) |
| Maximum output | 117,964 tokens (118K) |
| Tool calling | yes |
| Image input | no |
| Reasoning | no |
| First listed | 23 July 2024 |
Meta's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Llama Guard 4 12B | $0.18 | $0.18 | 160K | 30 April 2025 |
| Llama 4 Maverick | $0.1875 | $0.6525 | 512K | 5 April 2025 |
| Llama 4 Scout | $0.10 | $0.30 | 320K | 5 April 2025 |
| Llama 3.3 70B Instruct | $0.10 | $0.32 | 128K | 6 December 2024 |
| Llama 3.2 1B Instruct | $0.027 | $0.201 | 60K | 25 September 2024 |
| Llama 3.2 3B Instruct | $0.05 | $0.33 | 128K | 25 September 2024 |
| Llama 3.1 70B Instruct | $0.40 | $0.40 | 128K | 23 July 2024 |
Where these numbers come from
Read from OpenRouter's listing of Llama 3.1 8B Instruct every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.