Skip to content
LLMs

o1-pro vs Magnum v4 72B

Magnum v4 72B is 84× cheaper than o1-pro on a blended basis. o1-pro has the larger context window at 200K tokens.

OpenAI logo
o1-pro

OpenAI

$150

per 1M input tokens

Magnum v4 72B logo
Magnum v4 72B

Magnum v4 72B

$2.50

per 1M input tokens

Side by side

Green marks the better value in each row where a comparison is meaningful.

OpenAI: o1-pro compared with Magnum v4 72B
Attributeo1-proMagnum v4 72B
ProviderOpenAIMagnum v4 72B
Input / 1M tokens$150$2.50
Output / 1M tokens$600$5.00
Blended / 1M tokens$263$3.13
Cached input / 1M--
Context window200K33K
Max output100K4K
Input modalitiestext, image, filetext
ReasoningYesNo
Tool callingNoNo
Structured outputYesYes
Prompt cachingNoNo
Open weightsNoYes
Knowledge cutoff2023-10-312024-06-30
ReleasedMarch 19, 2025October 22, 2024

Frequently asked

Is o1-pro or Magnum v4 72B cheaper?

Magnum v4 72B is 84× cheaper than o1-pro on a blended basis.

What is the price difference between o1-pro and Magnum v4 72B?

o1-pro costs $150 per million input tokens and $600 per million output tokens. Magnum v4 72B costs $2.50 and $5.00 respectively.

Which has the larger context window, o1-pro or Magnum v4 72B?

o1-pro, at 200K tokens versus 33K.