anthracite-org

Magnum v4 72B

This AI model, Magnum v4 72B, is designed for text-based input and processing, with a context length of up to 32,768 tokens. It does not support tools or reasoning capabilities, nor does it produce structured output. Given its price point of $2.5 per million input tokens and $5.0 per million output tokens, Magnum v4 72B is likely to appeal to users who require a high-capacity text processing system and are willing to pay for it. However, as there is currently no benchmark coverage available for this model, its performance in comparison to other models cannot be assessed at this time.

Quality Score
60/100
price + capability + benchmarks
Input Price
$2.50
per 1M tokens · checked 2026-09-23
Output Price
$5.00
per 1M tokens · checked 2026-09-23
Context Window
32,768
tokens
Model ID
anthracite-org/magnum-v4-72b
Vendor
anthracite-org
Released
October 2024
Tokenizer
Qwen
Input Modalities
text
Output Modalities
text
Max Output
4,096 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $2.50/M input and $5.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.08
Classify 1,000 customer emails 500k in / 50k out $1.50
A month of a busy support chatbot 5M in / 2M out $22.50

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-09-01 $2.50 $5.00 32,768
2026-08-14 $3.00 $5.00 32,768
2026-07-22 $3.00 $5.00 16,384
2026-07-17 $3.00 $5.00 32,768

Quick answers

How much does Magnum v4 72B cost?
$2.50 per million input tokens and $5.00 per million output tokens.
What is Magnum v4 72B's context window?
32,768 tokens, roughly 49 pages of text in a single request.
Does Magnum v4 72B support tool calling?
It supports structured output.
Can Magnum v4 72B process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.