Hermes 4 (Thinking)
by NanoGPT · listed Sep 2025
General-purpose chat model for instruction following, writing, and analysis
Current rates USD per 1M tokens
Input$0.201
Output$0.40
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
NousResearch/Hermes-4-70B:thinking- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-09-17
- Last updated
- 2025-09-17
← All NanoGPT listings