Magnum v4 72B

ANTHRACITE-ORG Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1502Chatbot Arena Verified

Max Context Limit32,768Max Out: 4,096 tokens

Prompt CachingStandardNo Cache Discount

Standard API / 1M$7.50Blended Standard Rate

Model Capabilities & Contract SLAs

Coding & Logic
Fictional

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

Granular Pricing Matrix

Input Tokens (Standard Prompt)$2.50 / 1M

Output Tokens (Completion)$5.00 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupMagnum v4 72B vs Google: Gemini 3.7 Flash (batch)VS Engine MatchupMagnum v4 72B vs Google: Gemini 3.5 Flash Lite VS Engine MatchupMagnum v4 72B vs Sao10K: Llama 3.1 Euryale 70B v2.2 VS Engine MatchupMagnum v4 72B vs OpenAI: GPT-5.6 Sol Pro VS Engine MatchupMagnum v4 72B vs OpenAI: GPT-5.5 (batch)VS Engine MatchupMagnum v4 72B vs OpenAI: GPT-5.4 (batch)