opendunes

Magnum v4 72B

by Anthracite OrgReleased 22 October 2024

Magnum v4 72B is a model retrained from Qwen2.5 to write with the prose quality of Claude 3 Sonnet and Opus. Give it a story premise, a scene to continue or a style to imitate, and it writes literary-sounding fiction. It reads about 30 pages, replies up to about 4 pages, and lets you adjust how varied and how repetitive its wording is. It cannot use connected tools; for long inputs or code, pick a general model.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 1,66 DA per message3 000 DA buys about 1 800 messages

One message, the ordinary use

1 000 tokens sent× 832,09 DA per 1M0,83 DA
500 tokens back× 1 664,18 DA per 1M0,83 DA
Total≈ 1,66 DA

Every rate

Meter↑ you send↓ comes back
Text tokens832,09 DA1 664,18 DA
Cached tokens read832,09 DA

per 1M tokens

Answer a quick question≈ 0,54 DA
Write a one-page draft≈ 1,75 DA
Continue a role-play scene≈ 2,33 DA
Write a 1 000-word short story≈ 2,50 DA
Rewrite a scene in a new tone≈ 3,00 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.

Mancer 2…
↑ Sent, per 1M
832,09 DA
↓ Back, per 1M
1 664,18 DA
Cache read
832,09 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Mancer 2832,09 DA1 664,18 DA832,09 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
anthracite-org/magnum-v4-72b
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="anthracite-org/magnum-v4-72b",
    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_kmin_ptop_astopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Questions about Magnum v4 72B

  • How much does Magnum v4 72B cost in dinars?

    About 1,66 DA per message. ↑ 832,09 DA · ↓ 1 664,18 DA per 1M tokens.

  • Is Magnum v4 72B 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 Magnum v4 72B best for?

    Magnum v4 72B is a model retrained from Qwen2.5 to write with the prose quality of Claude 3 Sonnet and Opus. Give it a story premise, a scene to continue or a style to imitate, and it writes literary-sounding fiction. It reads about 30 pages, replies up to about 4 pages, and lets you adjust how varied and how repetitive its wording is. It cannot use connected tools; for long inputs or code, pick a general model.

  • How do I pay for Magnum v4 72B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Magnum v4 72B included, is paid from that balance. No foreign card, no conversion.

  • Does Magnum v4 72B work in Arabic, French or Darja?

    The model card tags English. Arabic, French and Darja are not named.

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

    It reads text. Up to 33K tokens in one request, about 32 pages. It writes up to 3 000 words at once.

  • Is Magnum v4 72B open source?

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

  • Who makes Magnum v4 72B, and when was it released?

    Anthracite Org. Released 22 October 2024. It knows the world up to 30 June 2024.