Skip to main content
Available now on ModelsLab · Language Model

Nous: Hermes 3 405B InstructSteer Frontier Reasoning

Try Nous: Hermes 3 405B InstructAPI Documentation

Unlock Hermes Capabilities

131K Context

Process Long Inputs

Handle 131K token context for multi-turn conversations and long documents.

Agentic Power

Enable Advanced Agents

Supports function calling, roleplaying, and structured outputs in Nous: Hermes 3 405B Instruct.

16K Output

Generate Detailed Responses

Produce up to 16K tokens per response for complex reasoning and code tasks.

Examples

See what Nous: Hermes 3 405B Instruct can create

Copy any prompt below and try it yourself in the playground.

Code Refactor

“Refactor this Python function for efficiency and add type hints: def calculate_fib(n): if n <= 1: return n; return calculate_fib(n-1) + calculate_fib(n-2)”

JSON Schema

“Generate a JSON schema for a user profile with fields: name, email, age, preferences as array of strings. Include validation rules.”

Logic Puzzle

“Solve this riddle step-by-step: Three houses in a row, owned by Brit, Swede, Dane. Colors red, green, white. Drinks tea, coffee, milk. Pets dog, birds, cats. Who owns the fish?”

Essay Outline

“Create a detailed outline for a 2000-word essay on quantum computing impacts on cryptography, with sections for history, algorithms, and future risks.”

For Developers

A few lines of code.
Reasoning. Few lines.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per token, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())

FAQ

Common questions about Nous: Hermes 3 405B Instruct

Read the docs

Nous: Hermes 3 405B Instruct is a 405B parameter fine-tune of Llama-3.1-405B by Nous Research. It excels in agentic tasks, reasoning, roleplaying, and code generation. Competitive with top instruct models.

Access via OpenAI-compatible endpoints with JavaScript, Python, or cURL. Include the library and call with model ID nousresearch/hermes-3-llama-3.1-405b. No backend setup needed.

Supports 131K tokens for input. Enables long context coherence and multi-turn dialogues. Max output reaches 16K tokens.

Input and output cost $1 per million tokens. Free tiers available on some platforms. Check endpoint for current rates.

Available on Hugging Face as nousresearch/Hermes-3-Llama-3.1-405B. Full-parameter fine-tune with Llama 3.1 license terms.

Offers superior user alignment, steering, and function calling over Llama-3.1 Instruct. Strong in STEM, logic, and creativity tasks.

Ready to create?

Start generating with Nous: Hermes 3 405B Instruct on ModelsLab.

Try Nous: Hermes 3 405B InstructAPI Documentation