Nous: Hermes 4 405B
nousresearch/hermes-4-405b
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...
Prompt $/1M
$1.000
Completion $/1M
$3.000
Context
131,072 tok
Best provider
24 tok/s · Nebius
Specs
- Model id
- nousresearch/hermes-4-405b
- Display name
- Nous: Hermes 4 405B
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 131,072
- Max completion
- —
- Prompt $/1M
- $1.000
- Completion $/1M
- $3.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Nebiusfastest | 24 |