Nous: Hermes 4 405B
Released Aug 26, 2025Try it on:
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
Per token
- Input (per 1M)
- $1.00
- Output (per 1M)
- $3.00
Capabilities
Modality
text->textContext
131K tokens
Tokenizer
Other
Knowledge cutoff
2024-08-31
Moderation
Unmoderated
Hugging Face
Supported parameters
frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
repetition_penalty
response_format
temperature
top_k
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.