Hermes 4 405B
Hermes 4 405B is a large-scale reasoning model developed by Nous Research based on Meta-Llama-3.1-405B. It features a hybrid reasoning mode that allows the model to deliberate internally before providing an output. The model supports a large context window of 131,072 tokens for text-based tasks.
Hermes 4 405B specs and pricing
- Provider: Nous
- Released: August 26, 2025
- Context window: 131K tokens
- Max output: 118K tokens
- Input: text
- Output: text
- Price: $1.00 input / $3.00 output per 1M tokens
- Reasoning: yes
What Hermes 4 405B is good at
- Complex logical reasoning tasks
- Processing large volumes of text data
- Applications requiring internal deliberation
To-dos to try with Hermes 4 405B
- Analyze a 100,000-word document and summarize the core arguments.
- Solve a multi-step mathematical proof requiring internal reasoning.
- Draft a detailed technical report based on a provided set of research notes.
FAQ
- Who developed Hermes 4 405B? The model was released by Nous Research and is built upon the Meta-Llama-3.1-405B architecture.
- What is the primary capability of this model? It is designed for large-scale reasoning and includes a hybrid mode that enables the model to deliberate internally.
- How much does Hermes 4 405B cost? Hermes 4 405B costs $1.00 per million input tokens and $3.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.22 credits ($1 = 100 credits).
- What is the context window of Hermes 4 405B? Hermes 4 405B can read up to 131K tokens at once and write up to 118K tokens in one reply.
- Can I use Hermes 4 405B without coding? Yes. In todo.is you pick Hermes 4 405B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.