Nous: Hermes 4 405Bnousresearch
Bottom Line
Nous: Hermes 4 405B: $1.00/1M input, $3.00/1M output, 131K context. 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...
API Pricing (per 1M tokens)
| Input | $1.00 |
| Output | $3.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.50 |
Specs & Performance
| Context Length | 131K |
| Max Output | 118K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from nousresearch
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Nous: Hermes 4 405B API cost?
Nous: Hermes 4 405B costs $1.00/1M input tokens and $3.00/1M output tokens. Blended cost at a 3:1 ratio is about $1.50/1M tokens.
What is the context window of Nous: Hermes 4 405B?
Nous: Hermes 4 405B supports a 131K token context window with up to 118K output tokens.
Is Nous: Hermes 4 405B worth it?
Nous: Hermes 4 405B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.