Skip to content
OpenKey

Hermes 4 70B

Nous ResearchReleased Aug 26, 2025

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

Try in playground
Context window
131K tokens
Input
text
Output
text
Tokenizer
Llama3
Knowledge cutoff
Aug 31, 2024
Released
Aug 26, 2025
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.130$0.0039$0.134
Output$0.400$0.012$0.412

Supported parameters

  • frequency_penalty
  • include_reasoning
  • max_tokens
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • temperature
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model nousresearch/hermes-4-70b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nousresearch/hermes-4-70b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="nousresearch/hermes-4-70b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "nousresearch/hermes-4-70b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Hermes 4 70B cost via API?
Through OpenKey, Hermes 4 70B costs $0.134 per 1M input tokens and $0.412 per 1M output tokens. That is the provider price ($0.130 / $0.400) plus a flat 3% fee — nothing else.
What is Hermes 4 70B's context window?
Hermes 4 70B accepts up to 131K tokens of context.
Is Hermes 4 70B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "nousresearch/hermes-4-70b" using any OpenAI SDK — only the base URL and API key change.
What inputs does Hermes 4 70B support?
Hermes 4 70B accepts text input and produces text output. Its knowledge cutoff is Aug 31, 2024.

More from Nous Research

All Nous Research models →