Skyfall 36B V2
VerifiedSkyfall 36B V2 offers capable text generation with a 32k-token context window.
About Skyfall 36B V2
Skyfall 36B V2 is built as a text-only LLM featuring a 32768-token context window. Its design prioritizes coherent handling of longer documents and conversations while remaining closed-source for controlled distribution. The 36B scale supports detailed language tasks without public weight access.
Strengths include sustained performance across extended contexts and reliable text generation suitable for professional use. Because it is not open-weight, the model allows Thedrummer to maintain quality control and offer tailored access options.
Typical usage covers content creation, analysis of lengthy texts, and integration into private systems where users require substantial context capacity without relying on open-source alternatives.
Capabilities
How Skyfall 36B V2 compares
Skyfall 36B V2 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Skyfall 36B V2 ranks #48 of 98
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long-context document summarization
Skyfall 36B V2 processes up to 32768 tokens, enabling coherent summaries of lengthy reports, research papers, or transcripts in a single pass.
Multi-turn technical conversations
The 36B parameter scale supports sustained reasoning across extended dialogues on coding, debugging, or system architecture topics.
Creative writing with continuity
Its context window maintains plot and character consistency across long-form stories, scripts, or world-building sessions.
Strengths & limitations
Strengths
- +Strong balance of capability and efficiency at 36B scale
- +Reliable handling of 32k token contexts
- +Versatile across general text tasks
- +Suitable for both chat and structured output
Limitations
- –Text-only modality with no vision or audio support
- –Context window capped at 32k tokens
- –Performance depends on specific fine-tuning quality
Cost calculator
Estimate what Skyfall 36B V2 would cost for your usage.
Based on Skyfall 36B V2's $0.55/1M input · $0.80/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "thedrummer/skyfall-36b-v2",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: thedrummer/skyfall-36b-v2
Editor's verdict
Skyfall 36B V2 is Thedrummer's proprietary language models with a 33K-token context window.
At $0.80 per 1M output tokens, it is very cost-efficient for its class.
It is available through Thedrummer's API and aggregators like OpenRouter.
Best suited to strong balance of capability and efficiency at 36b scale and reliable handling of 32k token contexts.
Frequently asked questions
The model provides a context window of 32768 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Similar models
Other language models worth comparing.