Llama 3.2 3b Instruct
nano-gpt / meta-llama/llama-3.2-3b-instruct
Input price
$0.0306
per 1M tokens
Output price
$0.0493
per 1M tokens
Context
131K
tokens
Capabilities
— Reasoning— Tool calls✓ Image input✓ Open weights
| cache read | $0.0153 |
| Context | 131,072 tokens |
| max output | 8,192 tokens |
| Released | 2024-09-25 |
| Data updated | 2024-09-25 |
⚠ The two sources disagree on price
models.dev says $0.0306, LiteLLM says $0.03. We do not average or guess — both raw values are in models.json, see for yourself.
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.