opendunes

Uncensored

by CognitivecomputationsReleased 9 July 2025

Venice Uncensored is Dolphin Mistral 24B, a text chat model whose behaviour you set entirely with the instructions you give it at the start: character, tone and rules are yours, and it follows them without added refusals. It keeps about 128 pages in mind and replies up to about 8 pages. Use it for fiction, role-play and edgy copy that other models decline; its maker suggests a low randomness setting, about 0.15. For customer-facing bots that need built-in safeguards, choose a different model.

TakesText
GivesText

What it costs

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

≈ 0,22 DA per message3 000 DA buys about 13 000 messages

One message, the ordinary use

1 000 tokens sent× 66,57 DA per 1M0,067 DA
500 tokens back× 299,55 DA per 1M0,15 DA
Total≈ 0,22 DA

Every rate

Meter↑ you send↓ comes back
Text tokens66,57 DA299,55 DA

per 1M tokens

Answer a quick question≈ 0,085 DA
Reply to a customer email≈ 0,16 DA
Translate a full page of text≈ 0,29 DA
Write a one-page draft≈ 0,29 DA
Summarise a 20-page report≈ 1,14 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.

VeniceUnited States…
↑ Sent, per 1M
66,57 DA
↓ Back, per 1M
299,55 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackLatencyThroughputUptime
VeniceUnited States66,57 DA299,55 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.

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
cognitivecomputations/dolphin-mistral-24b-venice-edition
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="cognitivecomputations/dolphin-mistral-24b-venice-edition",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

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

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_kstopfrequency_penaltypresence_penalty

Structured output

Get JSON you can parse instead of prose.

response_format

Questions about Uncensored

  • How much does Uncensored cost in dinars?

    About 0,22 DA per message. ↑ 66,57 DA · ↓ 299,55 DA per 1M tokens.

  • Is Uncensored 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 Uncensored best for?

    Venice Uncensored is Dolphin Mistral 24B, a text chat model whose behaviour you set entirely with the instructions you give it at the start: character, tone and rules are yours, and it follows them without added refusals. It keeps about 128 pages in mind and replies up to about 8 pages. Use it for fiction, role-play and edgy copy that other models decline; its maker suggests a low randomness setting, about 0.15. For customer-facing bots that need built-in safeguards, choose a different model.

  • How do I pay for Uncensored without an international card?

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

  • Does Uncensored work in Arabic, French or Darja?

    Cognitivecomputations names no languages for Uncensored. Arabic, French and Darja: not stated.

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

    It reads text. Up to 128K tokens in one request, about 120 pages. It writes up to 6 000 words at once.

  • Is Uncensored open source?

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

  • Who makes Uncensored, and when was it released?

    Cognitivecomputations. Released 9 July 2025. It knows the world up to 30 April 2024.