Skyfall 36B V2
Neural Network
Skyfall 36B V2 is a fine-tuned version of Mistral Small 2501 for creative writing, roleplay scenarios, and coherent storytelling.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Skyfall 36B V2?
Skyfall 36B V2 is a refined version of Mistral Small 2501, fine-tuned for creative tasks: more expressive and nuanced writing, compelling roleplay scenarios, and stories that don't fall apart as they progress. This specialization distinguishes it from the base model: the focus is shifted from universal tasks to creative text and character development. In BotHub, the model is available immediately, without VPN or foreign cards. You pay with a Russian card in rubles based on actual usage — for consumed tokens, without a subscription, and unused funds do not expire. Over 250 models are available in one window: you can send a draft to one and editing to another without changing tabs. For developers, there is a unified OpenAI-compatible API — switching models is as simple as changing the identifier. It is useful for writing novel chapters and short prose, conducting interactive roleplay stories and character dialogues, assembling plot threads and game lines, creating original advertising copy and video scripts, and describing worlds and character biographies.Frequently asked questions about Skyfall 36B V2
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
This is a text model by thedrummer with a 64,000 token context. It is suitable for writing and editing texts, working with code, analyzing large documents, and answering questions based on uploaded materials. You can input text, documents, and images.
Up to 29,491 tokens in a single response — enough for a lengthy article, detailed analysis, or a large code fragment. The total context window is 64,000 tokens, which includes both your request and attached files.
A separate step-by-step reasoning mode is not noted in our data. However, you can ask the model to break down the task step-by-step directly in the prompt — this technique usually significantly improves results for logic, calculations, and complex code.
Our data does not indicate support for function calling or strict structured output. If the format is important, describe the required schema directly in the prompt and verify the response with a validator. Through the unified BotHub API, you can always switch to a model with confirmed tool support.
Yes, the model accepts images and documents in addition to regular text — you can send a screenshot, diagram, or file and ask it to analyze the content. Audio and video are not listed as supported input formats; for those, BotHub's specialized models are suitable.
The model is built on a large language base and generally handles Russian-language queries well, but we do not have precise data on the quality of Russian specifically. Test it with your task: at BotHub, you pay per token, no subscription required.