Nous Research

Nous Research: Hermes 4 70B

nousresearch/hermes-4-70b

Access Hermes 4 70B from Nous Research using Puter.js AI API.

Get Started 
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "nousresearch/hermes-4-70b"
}).then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "nousresearch/hermes-4-70b"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="nousresearch/hermes-4-70b",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)

curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "nousresearch/hermes-4-70b",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Hermes 4 70B is a hybrid reasoning model based on Llama-3.1-70B with toggleable deep thinking mode using think tags. It offers major improvements in math, code, STEM, logic, and creative writing while supporting JSON schema adherence, function calling, and reduced refusal rates compared to other models.

Context Window 131K

tokens

Max Output 131K

tokens

Input Cost $0.13

per million tokens

Output Cost $0.4

per million tokens

Release Date Aug 18, 2025

 

Output Speed 66

tokens / sec

Latency 0.58s

time to first token

Model Playground

Try Hermes 4 70B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat nousresearch/hermes-4-70b
Nous Research
Chat with Hermes 4 70B
Powered by Puter.js

Benchmarks

How Hermes 4 70B performs on standard evaluations.

Artificial Analysis
Intelligence Index
12.6
Better than 26% of tracked models
Artificial Analysis
Coding Index
9.2
Better than 20% of tracked models
Artificial Analysis
Math Index
11.3
Better than 14% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
49.1%
Humanity's Last Exam Cross-domain reasoning
3.6%
LiveCodeBench Recent coding problems
26.9%
SciCode Scientific programming
27.7%
AIME 2025 Advanced math exam
11.3%
IFBench Instruction following
29.0%
LCR Long-context reasoning
2.0%
Terminal-Bench Hard Agentic terminal tasks
0.0%
τ²-Bench Tool use / agents
21.6%

Scores sourced from Artificial Analysis.

Find other Nous Research models →

Chat

Hermes 4 405B

Hermes 4 405B is a frontier hybrid-mode reasoning model based on Llama-3.1-405B, trained on a 60B token dataset with verified reasoning traces. It features toggleable deep reasoning via think tags, massive improvements in math, code, STEM, and logic, and achieves state-of-the-art on RefusalBench for reduced censorship.

 Chat

Hermes 3 405B Instruct

Hermes 3 Llama 3.1 405B is a frontier-level 405B parameter full fine-tune of Llama-3.1-405B, focused on user alignment with powerful steering capabilities. It features advanced agentic capabilities, roleplaying, reasoning, multi-turn conversation, and improved code generation, competitive with or superior to Llama-3.1 Instruct models.

 Chat

Hermes 3 70B Instruct

Hermes 3 Llama 3.1 70B is a 70B parameter fine-tune of Llama-3.1-70B offering advanced agentic capabilities, improved roleplaying, reasoning, and multi-turn conversation. It provides reliable function calling and structured outputs while being competitive with Llama-3.1 Instruct models at a more accessible size.

Frequently Asked Questions

How do I use Hermes 4 70B?

You can access Hermes 4 70B by Nous Research through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Hermes 4 70B free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Hermes 4 70B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Hermes 4 70B?
Pricing for Hermes 4 70B is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$0.13
Output$0.4
Who created Hermes 4 70B?

Hermes 4 70B was created by Nous Research and released on Aug 18, 2025.

What is the context window of Hermes 4 70B?

Hermes 4 70B supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Hermes 4 70B?

Hermes 4 70B can generate up to 131K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Hermes 4 70B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Hermes 4 70B to your app without worrying about API keys or setup.

Read the Docs View Tutorials