Magnum v4 72B

Anthracite

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. The model is fine-tuned on top of Qwen2.5 72B.

Try Now

Technical Specifications

Context Window

16,384 tokens

Max Output

2,048 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$3

Non-Reasoning Output

$5

Legacy

Made legacy on

Reason

Qwen2.5 72B fine-tune for creative writing; base model superseded by Qwen3.5

Recommended Replacement

Qwen3.6 Plus