opendunes

Hermes 4 405B

by NousresearchReleased 26 August 2025

Hermes 4 405B reads text and writes text back, and it keeps about 128 pages in mind at once. Built on Llama 3.1 405B, it can think out loud before answering or reply directly, depending on a setting. Its extra training, heavy on worked reasoning, aims at math, code, science and logic, and it fills in exact forms, calls the functions you connect and refuses less. Hermes 3 405B is its predecessor on the same base.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,83 DA per message3 000 DA buys about 3 600 messages

One message, the ordinary use

1 000 tokens sent× 332,84 DA per 1M0,33 DA
500 tokens back× 998,51 DA per 1M0,50 DA
Total≈ 0,83 DA

Every rate

Meter↑ you send↓ comes back
Text tokens332,84 DA998,51 DA
Cached tokens read66,57 DA

per 1M tokens

Answer a quick question≈ 0,30 DA
Reply to a customer email≈ 0,60 DA
Write a one-page draft≈ 1,00 DA
Explain a stack trace and suggest a fix≈ 1,10 DA
Solve a maths problem step by step≈ 1,60 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Nebius…
↑ Sent, per 1M
332,84 DA
↓ Back, per 1M
998,51 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Nebius332,84 DA998,51 DA66,57 DA………

You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
nousresearch/hermes-4-405b
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="nousresearch/hermes-4-405b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Questions about Hermes 4 405B

  • How much does Hermes 4 405B cost in dinars?

    About 0,83 DA per message. ↑ 332,84 DA · ↓ 998,51 DA per 1M tokens.

  • Is Hermes 4 405B free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Hermes 4 405B best for?

    Hermes 4 405B reads text and writes text back, and it keeps about 128 pages in mind at once. Built on Llama 3.1 405B, it can think out loud before answering or reply directly, depending on a setting. Its extra training, heavy on worked reasoning, aims at math, code, science and logic, and it fills in exact forms, calls the functions you connect and refuses less. Hermes 3 405B is its predecessor on the same base.

  • How do I pay for Hermes 4 405B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Hermes 4 405B included, is paid from that balance. No foreign card, no conversion.

  • Does Hermes 4 405B work in Arabic, French or Darja?

    Nous Research tags the model for English only. Arabic, French and Darja are not named.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 88 000 words at once.

  • Is Hermes 4 405B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Hermes 4 405B, and when was it released?

    Nousresearch. Released 26 August 2025. It knows the world up to 31 August 2024.