Magnum v4 72B
Magnum v4 72B is an AI model developed by anthracite-org, built upon the Qwen2.5 72B architecture. It is specifically designed to replicate the prose quality found in Claude 3 models. The model processes text inputs and generates text outputs.
Magnum v4 72B specs and pricing
- Provider: anthracite-org
- Released: October 22, 2024
- Context window: 33K tokens
- Max output: 4K tokens
- Input: text
- Output: text
- Price: $2.50 input / $5.00 output per 1M tokens
What Magnum v4 72B is good at
- Generating high-quality creative prose
- Writing tasks that require specific stylistic mimicry
- Long-form text generation within a 32,768 token context window
To-dos to try with Magnum v4 72B
- Write a short story chapter in the style of a professional novelist
- Draft a formal email based on a provided outline
- Rewrite a technical document to improve its narrative flow and readability
FAQ
- What is the primary purpose of Magnum v4 72B? The model is designed to replicate the prose quality of Claude 3 Sonnet and Opus models.
- What base architecture does this model use? Magnum v4 72B is fine-tuned on top of the Qwen2.5 72B instruct model.
- How much does Magnum v4 72B cost? Magnum v4 72B costs $2.50 per million input tokens and $5.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 7.7 credits ($1 = 100 credits).
- What is the context window of Magnum v4 72B? Magnum v4 72B can read up to 33K tokens at once and write up to 4K tokens in one reply.
- Can I use Magnum v4 72B without coding? Yes. In todo.is you pick Magnum v4 72B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.