Nous: Hermes 4 405B
by Nous ResearchNous: Hermes 4 405B is a large language model from Nous Research. It costs $1.00 per million input tokens and $3.00 per million output tokens. Its context window is 131K tokens.
ReasoningStructured outputOpen weights
- Input / 1M tokens
- $1.00
- Output / 1M tokens
- $3.00
- Cached input / 1M
- -
- Context window
- 131K
Not supported
tokens
Who serves it cheapest
1 hosts serve Hermes 4 405B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| NebiusCheapestfp8 | $1.00 | $3.00 | 131K | - | 100.0% |
About 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...
Specifications
| Model ID | nousresearch/hermes-4-405b |
|---|---|
| Provider | Nous Research |
| Context window | 131K tokens |
| Max output | 118K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2024-08-31 |
| Open weights | Yes - NousResearch/Hermes-4-405B |
| Released | August 26, 2025 |
Cheaper alternatives
Models that cost less than Hermes 4 405B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Nous: Hermes 4 405B cost?
$1.00 per million input tokens and $3.00 per million output tokens.
What is the context window of Nous: Hermes 4 405B?
131K tokens, with up to 118K tokens of output per request.