Llama 3.2 3b Instruct
by NanoGPT · family llama · listed Sep 2024W
Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval
Current rates USD per 1M tokens
Input$0.05
Output$0.33
Cache read$0.025
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
meta-llama/llama-3.2-3b-instruct- Context window
- 131K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-09-25
- Last updated
- 2024-09-25
← All NanoGPT listings