Nous · live price
Hermes 4 405B API pricing
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...
Mid-range ($1–5 per 1M)Reasoning
- Input
- $1
- per 1M tokens
- Output
- $3
- per 1M tokens
- Cached input
- $0.2
- per 1M tokens
- Context
- 131K
- 118K max output
List price from OpenRouter, which passes Nous's price through without markup. Refreshed hourly. Released August 26, 2025. Model id nousresearch/hermes-4-405b.
What Hermes 4 405B costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$2.50
1,000 input + 500 output tokens each
1,000 RAG questions
$9.50
8,000 input + 500 output tokens each
100 coding-agent steps
$3.60
30,000 input + 2,000 output tokens each, no caching
Hermes 4 405B price history
No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.
Hermes 4 405B price by host
One host serves this model through OpenRouter.
- Nebius$1 in · $3 out · 131K ctx · 100.0% uptime 24h
Where to buy Nous credits for less
Hermes 4 405B costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Hermes 4 405B cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$80.00/ month
Cheaper alternatives to Hermes 4 405B
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Z.ai: GLM 5.3 FlashX Legal | $0.37 | $1.25 |
| MiniMax: MiniMax M3.1 Flash | $0.15 | $0.6 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| Mistral: Mistral Large 4 | $0.7 | $2.10 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |