Magnum v4 72B vs Gemini 3.1 Pro Preview Custom Tools

Magnum v4 72B at $3.45 in and $5.75 out and Gemini 3.1 Pro Preview Custom Tools at $2.30 in and $13.80 out — per million tokens, from the same wallet.

Magnum v4 72B

Anthracite

2.2¢

for a client proposal

$3.45 in · $5.75 out / 1M

16K context · released October 2024

Full page →

Gemini 3.1 Pro Preview Custom Tools

Google

2.3¢

for a client proposal

$2.30 in · $13.80 out / 1M

1.05M context · released 5 months ago

Full page →

Asking all both at once — identical prompt, identical context — costs about 4.4¢ for a typical client proposal.

At a glance

Cheapest input: Gemini 3.1 Pro Preview Custom Tools at $2.30 per million tokens.
Cheapest output: Magnum v4 72B at $5.75 per million tokens.
Largest context: Gemini 3.1 Pro Preview Custom Tools at 1.05M tokens — about 1,500 pages.

Cost per task

Estimated totals at the rates above. Solid bar is input, lighter bar is output.

Quick code fix

2K in · 500 out

Magnum v4 72B

0.98¢

Gemini 3.1 Pro Preview Custom Tools

1.1¢

Draft a client proposal from notes

5K in · 800 out

Magnum v4 72B

2.2¢

Gemini 3.1 Pro Preview Custom Tools

2.3¢

Context-heavy session (Alyph workspace)

155K in · 4K out

Magnum v4 72B

needs 155K ctx

Gemini 3.1 Pro Preview Custom Tools

$0.41

Analyze a 50-page legal contract

35K in · 1K out

Magnum v4 72B

needs 35K ctx

Gemini 3.1 Pro Preview Custom Tools

$0.09

Large architecture refactor

250K in · 3K out

Magnum v4 72B

needs 250K ctx

Gemini 3.1 Pro Preview Custom Tools

$1.21

Long-context rate applied at this input size.

Solid part of each bar is input tokens, the lighter part is output. Models that don’t fit a task are marked instead of priced.

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output

Magnum v4 72B

Gemini 3.1 Pro Preview Custom Tools

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

Pricing

Magnum v4 72B

Gemini 3.1 Pro Preview Custom Tools

Input / 1M tokens

$3.45

$2.30

Output / 1M tokens

$5.75

$13.80

Cached input / 1M

—

$0.230

Web search

—

1.6¢ / search

Specs

Magnum v4 72B

Gemini 3.1 Pro Preview Custom Tools

Provider

Anthracite

Google

Released

October 2024

5 months ago

Context window

16K

1.05M

Max output

66K

Input

Text

Text, Audio, Images, Video, and Files

Output

Text

Reasoning

Answers directly

Shows its thinking

Knowledge cutoff

2024-06-30

—

Try it with real numbers

2K tokens in · 500 tokens out.

Magnum v4 72B

Anthracite

0.98¢

for this task

71% input · 29% output

Full pricing →

Gemini 3.1 Pro Preview Custom Tools

Google

1.1¢

for this task

40% input · 60% output

Full pricing →

All 2, same prompt and context: 2.1¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 235 of these.

Which should you pick?

For long documents, Gemini 3.1 Pro Preview Custom Tools has the largest context window here — 1.05M tokens.

On price, Magnum v4 72B is the cheapest of the two on a typical task, at about 2.2¢.

For images or files, Gemini 3.1 Pro Preview Custom Tools can read them directly; Magnum v4 72B is text-only.

If you want to watch the model think, Gemini 3.1 Pro Preview Custom Tools shows reasoning; the other answers directly.

Or don’t pick. Send the identical prompt to all both, read the answers side by side, and keep the winner. How to run a fair bake-off →

Magnum v4 72B pricing →Gemini 3.1 Pro Preview Custom Tools pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Magnum v4 72B or Gemini 3.1 Pro Preview Custom Tools?

On a typical client proposal (5K tokens in, 800 out): Magnum v4 72B at 2.2¢; Gemini 3.1 Pro Preview Custom Tools at 2.3¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

Gemini 3.1 Pro Preview Custom Tools — 1.05M tokens, about 1,500 pages.

Can I run Magnum v4 72B and Gemini 3.1 Pro Preview Custom Tools side by side on Alyph?

Yes — that is what Alyph is built for: the identical prompt with identical context to all 2, answers rendered side by side, billed from one wallet. This exact combination costs about 4.4¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 4.4¢ for a typical client proposal. Free to start, with $5 of credit.