← model directory

nousresearch

Nous: Hermes 4 405B

nousresearch/hermes-4-405b

↓ runs free on your own hardware

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...

specs & pricing
Type
text
Provider
nousresearch
Model ID
nousresearch/hermes-4-405b
Capabilities
reasoning
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$1.10 / 1M tokens
Output price
$3.30 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$4.40

$1.10 for a million input tokens plus $3.30 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for Nous: Hermes 4 405B (405B parameters), for the weights alone — add room for the context cache.

Q4_K_M
~230.8 GBmulti-GPU or large unified memory
Q8_0
~400.6 GBmulti-GPU or large unified memory
FP16 / BF16
~755.1 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call Nous: Hermes 4 405B through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Nous: Hermes 4 405B?
Nous: Hermes 4 405B accepts up to 131,072 tokens (131K) of context per request.
How much does Nous: Hermes 4 405B cost per million tokens?
Through Wide Area Intelligence, Nous: Hermes 4 405B costs $1.10 per 1M input tokens and $3.30 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $4.40.
Can I run Nous: Hermes 4 405B on my own hardware?
Yes — Nous: Hermes 4 405B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 230.8 GB of GPU memory, plus room for the context cache — more than a single 80 GB card, so plan for multiple GPUs or a large unified-memory machine. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from nousresearch

← browse all models