Nous Research

Discover Nous Research Hermes models for advanced reasoning and instruction following

You can get an API key from the Nous Research Portal.

Available Models

Model	Context Length	Description
`Hermes-4.3-36B`	128k	Compact reasoning model with thinking capabilities
`Hermes-4-70B`	128k	Large reasoning model with 128k context
`Hermes-4-405B`	128k	Flagship reasoning model
`Hermes-3-Llama-3.1-70B`	32k	Instruction-tuned on Llama 3.1 70B
`Hermes-3-Llama-3.1-405B`	32k	Instruction-tuned on Llama 3.1 405B

Configuration

name: My Config
version: 0.0.1
schema: v1

models:
  - name: Hermes 4.3 36B
    provider: nous
    model: Hermes-4.3-36B
    apiKey: <YOUR_NOUS_API_KEY>

Reasoning Mode

Hermes 4 and DeepHermes models support reasoning with chain-of-thought. To enable reasoning, use the following system prompt:

You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

name: My Config
version: 0.0.1
schema: v1

models:
  - name: Hermes 4.3 36B (Reasoning)
    provider: nous
    model: Hermes-4.3-36B
    apiKey: <YOUR_NOUS_API_KEY>
    systemMessage: |
      You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

Mistral NVIDIA