Turn this customer email into JSON with intent, urgency and order_id.
customer-email.txtSkyfall 36B V2
by ThedrummerReleased 10 March 2025
Skyfall 36B V2 takes text and writes text, and keeps about 30 pages of story in mind at once. It is a retrained version of Mistral Small 2501, aimed at imaginative writing, role-play and stories that hold together from start to finish. Pick it for fiction and character chat. Cydonia 24B V4.1 keeps about 130 pages in mind, which suits longer stories, and UnslopNemo 12B is aimed at adventures.
What it costs
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 183,06 DA | 266,27 DA |
| Cached tokens read | 83,21 DA |
per 1M tokens
- 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.
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.
You pay the price of the provider that served your request. Prices read 15:19 · 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.
Two lines to welcome a shop in Oran.
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 LabTry your own request — same model, pre-selected.
Open Chat LabCall it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
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="thedrummer/skyfall-36b-v2",
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_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobsStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsQuestions about Skyfall 36B V2
How much does Skyfall 36B V2 cost in dinars?
About 0,32 DA per message. ↑ 183,06 DA · ↓ 266,27 DA per 1M tokens.
Is Skyfall 36B V2 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 Skyfall 36B V2 best for?
Skyfall 36B V2 takes text and writes text, and keeps about 30 pages of story in mind at once. It is a retrained version of Mistral Small 2501, aimed at imaginative writing, role-play and stories that hold together from start to finish. Pick it for fiction and character chat. Cydonia 24B V4.1 keeps about 130 pages in mind, which suits longer stories, and UnslopNemo 12B is aimed at adventures.
How do I pay for Skyfall 36B V2 without an international card?
Deposit dinars with your Edahabia or CIB card. Every model, Skyfall 36B V2 included, is paid from that balance. No foreign card, no conversion.
Does Skyfall 36B V2 work in Arabic, French or Darja?
Thedrummer names no languages for Skyfall 36B V2. Arabic, French and Darja: not stated.
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 22 000 words at once.
Is Skyfall 36B V2 open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes Skyfall 36B V2, and when was it released?
Thedrummer. Released 10 March 2025. It knows the world up to 30 June 2024.
Other Thedrummer models, priced in dinars
See all Thedrummer modelsCydonia 24B V4.1 takes text and writes text, and keeps about 130 pages of story or chat in mind at once. It is a creative-writing and role-play model made from Mistral Small 3.2, described as uncensored, with good memory for what came earlier and close attention to what you ask. Pick it for fiction, character chat and story drafts. UnslopNemo 12B is the specialist for adventure stories.
UnslopNemo 12B takes text and writes text, and is written for adventure stories and role-play, where you play a character or steer the plot and the model carries it on. It is version 4.1, from the same maker as Rocinante. Pick it for text adventures and interactive fiction. Cydonia 24B V4.1 and Skyfall 36B V2 are the other two creative-writing models from the same maker, aimed at fiction and character chat.
