Skyfall 36B v2
Skyfall 36B v2 by TheDrummer is a depth-upscaled Mistral Small 2501 — 36B parameters instead of 24B — with continued training for creativity and roleplay: nuanced writing, coherent long stories, staying in character. It is a hobbyist release with an unspecified licence, no benchmarks and no safety statement, so treat it as a writing tool and clarify commercial rights before relying on it. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: skyfall-36b
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="skyfall-36b", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "skyfall-36b", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "skyfall-36b", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- TheDrummer
- Released
- February 2025
- Licence
- not declared on the model card
- Architecture
- dense · 36B parameters
- Based on
- Mistral Small 24B (2501)
- Input
- text
- Reasoning
- no reasoning mode
- Languages named by the developer
- none named on the model card
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
The model card declares no licence. Without one, the right to use the weights commercially is unclear — clarify it before you build a product on this model.
A summary of the licence, not legal advice.
Technical details
- Context window
- 32K tokens
- Max output
- 32,768 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Mistral
- Streaming
- yes
- Open weights
- TheDrummer/Skyfall-36B-v2
- max_tokens
- 1 … 32768
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is Skyfall 36B v2 computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does Skyfall 36B v2 store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Skyfall 36B v2 context window?
32K tokens, with up to 32,768 tokens of output.
›What does Skyfall 36B v2 cost?
$0.71 per million input tokens and $1.13 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Skyfall 36B v2?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Skyfall 36B v2 support?
The developer's model card names no languages. Test the model on your own material before relying on it in a particular language.
›Under which licence is Skyfall 36B v2 released?
The model card declares no licence. Without one, the right to use the weights commercially is unclear — clarify it before you build a product on this model.
›Can reasoning be switched off in Skyfall 36B v2?
Skyfall 36B v2 has no reasoning mode — it answers directly, which keeps latency and output tokens low.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Skyfall 36B v2 | TheDrummer | 36B | 32K | — | $0.71 |
| Cydonia 24B v4.1 | TheDrummer | 24B | 128K | — | $0.42 |
| Qwen3.6 35B A3B | Qwen (Alibaba) | 35B / 3B | 256K | Apache-2.0 | $0.15 |
| Qwen3 32B | Qwen (Alibaba) | 32.8B | 128K | Apache-2.0 | $0.12 |
30 more models behind the same key and the same invoice.
Browse the catalog