Magnum V4 72B
Neural Network
Magnum V4 72B is a Qwen2.5 72B-based model fine-tuned for creative writing: magnum v4 72b api for writing tasks.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Magnum V4 72B?
Magnum V4 72B is a fine-tuned version of Qwen2.5 72B from the Magnum series, created with one goal: to bring the quality of creative prose closer to that of large closed models. It differs from the base model through writing-focused tuning: vivid descriptions, consistent narrative style, and natural dialogue instead of dry assistant responses. The 72 billion parameter size provides headroom for long, coherent scenes. In BotHub, the model works without a VPN or foreign card, and you pay in rubles as you go — for consumed tokens, without a subscription, and the balance does not expire. Over 250 models are available in one window: you can start a draft here and hand off fact-checking to another model without changing services. For products, there is a unified OpenAI-compatible API; for companies, we offer contracts, invoices, and an admin panel with limits. Simple scenarios: scene and dialogue templates, story and chapter drafts, texts for game worlds and interactive stories, rewriting fragments in a different tone, and character lines for chatbot companions.Frequently asked questions about Magnum V4 72B
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 from anthracite-org with a 32,768 token context. It is suitable for generating and editing text, dialogues, and narrative scenarios, parsing documents, and working with code. You can input not only text but also images and documents.
The output limit is 4096 tokens per response, which is several pages of text. If you need voluminous material, break the task into parts: the 32,768 token context allows you to keep previous fragments in the dialogue and continue without losing coherence.
A separate reasoning mode is not noted in our data. However, you can ask the model to break down the solution step-by-step directly in the prompt — this usually results in more accurate answers for logical and analytical tasks. If you specifically need reasoning models, switch to another one in the same BotHub window.
Support for function calling and strict JSON mode is not noted in our data. For reliable structured responses, describe the required format in the prompt and validate the result on your end, or choose a model with confirmed function calling — BotHub has a unified API.
The model accepts images and documents as input: you can ask it to describe an image or parse a file's content. There are no notes in our data regarding audio or video. You receive text as output — image, audio, or video generation is not supported here.
The model is built on the multilingual Qwen2.5-72B base, so it generally handles Russian queries well. It is easy to check the quality with your own task: in BotHub, you open magnum v4 72b without a VPN or foreign card, pay in rubles, and compare it with another model in the same window if necessary.