---
id: "anthracite-org/magnum-v4-72b"
also: ["anthracite-org/magnum-v4-72b"]
cheapest_list_usd_per_m: "2.5 in, 5.0 out, at mancer/fp8 on openrouter"
cheapest_effective_usd_per_m: "2.4999 in, 5.0 out, at mancer/fp8 on openrouter"
context: 32768
max_output: 4096
input: ["text"]
output: ["text"]
released: "2024-10-22"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_a", "top_k", "top_logprobs", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# Magnum v4 72B

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).