modelgrep
A

Magnum v4 72B

anthracite-org/magnum-v4-72b

JSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
26
250th fastest
Latency
1.2s
first token
Input price
$3.00
270th cheapest
Context
33K
2K max out

How it compares

Faster than15%
of all ranked models
Cheaper than9%
of all ranked models

Overview

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).

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mancer 2fp8$3.00$5.00

Specifications

Context window33K
Max output2K
Knowledge cutoffJun 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Magnum v4 72B FAQ

How much does Magnum v4 72B cost?

Magnum v4 72B costs $3.00 per million input tokens and $5.00 per million output tokens via OpenRouter, making it 270th cheapest of 298 paid models.

How fast is Magnum v4 72B?

Magnum v4 72B generates around 26 tokens per second with 1.2s time-to-first-token (p50), the 250th fastest tracked model.

What is Magnum v4 72B's context window?

Magnum v4 72B supports a 33K-token context window and can output up to 2K tokens. It accepts text input.