# Hermes 3 405B Instruct

> Hermes 3 405B Instruct is an open-weight language model from Nousresearch, released on 16 Aug 2024. It accepts text and generates text, with a 131K-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $1 per million input tokens and $1 per million output tokens (OpenRouter), across 1 provider we track.

Source page: https://www.aimodel.directory/models/hermes-3-llama-3-1-405b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Nousresearch
- **Release date:** 16 Aug 2024 (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Status:** Generally available
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B)
- **License:** llama3 (source: Hugging Face, https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B)
- **Parameters:** 406B (source: Hugging Face, https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B)
- **Context window:** 131K (131,072 tokens) (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Max output:** 16K tokens (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Knowledge cutoff:** 31 Dec 2023 (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Input:** Text (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Output:** Text (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Reasoning mode:** No (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Tool calling:** No (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Structured output:** Yes (source: OpenRouter, https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b)
- **Hugging Face:** NousResearch/Hermes-3-Llama-3.1-405B (source: Hugging Face, https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $1 | $1 | – | 131K |

## FAQ

### What is the context window of Hermes 3 405B Instruct?

Hermes 3 405B Instruct has a context window of 131,072 tokens (131K) and can generate up to 16,384 tokens in a single response, according to OpenRouter.

### How much does the Hermes 3 405B Instruct API cost?

Hermes 3 405B Instruct is listed from $1 per million input tokens and $1 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is Hermes 3 405B Instruct open source?

Hermes 3 405B Instruct is an open-weight model: its weights are published on Hugging Face as NousResearch/Hermes-3-Llama-3.1-405B under the llama3 license. Check the license terms before commercial use.

### When was Hermes 3 405B Instruct released?

Nousresearch released Hermes 3 405B Instruct on 16 Aug 2024, according to OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Hermes 3 405B Instruct", https://www.aimodel.directory/models/hermes-3-llama-3-1-405b