Llama 3.2 Instruct 3B is a text-based AI model by Meta. It features 51 tok/s output speed, $0.08/1M input tokens pricing. It scores 9.7 on the intelligence index.
Output Speed
51 tok/s
Latency (TTFT)
0.38s
Blended Price
$0.09/M
| Input (Prompt) | $0.08 |
| Output (Completion) | $0.08 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Llama 3.2 Instruct 3B costs $0.08/1M input tokens and $0.08/1M output tokens.
Llama 3.2 Instruct 3B generates output at 51 tok/s. Time to first token is 0.38s.
No, Llama 3.2 Instruct 3B is a paid model. Check the free models page for zero-cost alternatives.
See the alternatives section above for models with similar capabilities. You can also compare Llama 3.2 Instruct 3B head-to-head with any model on our comparison page.
Last updated: