Hermes 2 Pro Llama 3 8B
by Helicone · family hermes · listed Apr 2024TW
Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue
Current rates USD per 1M tokens
Input$0.14
Output$0.14
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
hermes-2-pro-llama-3-8b- Context window
- 131K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- May 2024
- Released
- 2024-04-30
- Last updated
- 2024-04-30
← All Helicone listings