AI Observatory / Model Radar
Nousresearch / nousresearch/hermes-4-405b
Nous: 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...
131,072
Context
N/A
Max output
$1.00 / 1M
Prompt price
2025-08-26
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Nousresearch | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $1.00 / 1M |
| Completion price | $3.00 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | N/A |
| Supported parameters | frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, temperature, top_k, top_p | ||
Best for
nousresearch/hermes-4-405b
Nous: 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...
Deep analysis
High-volume usage
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.