Mercury 2 vs MiniMax-01

Mercury 2 at $0.287 in and $0.863 out and MiniMax-01 at $0.230 in and $1.26 out — per million tokens, from the same wallet.

Mercury 2

Inception

0.21¢

for a client proposal

$0.287 in · $0.863 out / 1M

128K context · released 5 months ago

Full page →

MiniMax-01

MiniMax

0.22¢

for a client proposal

$0.230 in · $1.26 out / 1M

1M context · released January 2025

Full page →

Asking all both at once — identical prompt, identical context — costs about 0.43¢ for a typical client proposal.

At a glance

Cheapest input: MiniMax-01 at $0.230 per million tokens.
Cheapest output: Mercury 2 at $0.863 per million tokens.
Largest context: MiniMax-01 at 1M tokens — about 1,400 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

Mercury 2

0.1¢

MiniMax-01

0.11¢

Draft a client proposal from notes

5K in · 800 out

Mercury 2

0.21¢

MiniMax-01

0.22¢

Context-heavy session (Alyph workspace)

155K in · 4K out

Mercury 2

needs 155K ctx

MiniMax-01

4.1¢

Analyze a 50-page legal contract

35K in · 1K out

Mercury 2

1.1¢

MiniMax-01

0.93¢

Large architecture refactor

250K in · 3K out

Mercury 2

needs 250K ctx

MiniMax-01

$0.06

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

Mercury 2

MiniMax-01

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

Pricing

Mercury 2

MiniMax-01

Input / 1M tokens

$0.287

$0.230

Output / 1M tokens

$0.863

$1.26

Cached input / 1M

$0.029

—

Specs

Mercury 2

MiniMax-01

Provider

Inception

MiniMax

Released

5 months ago

January 2025

Context window

128K

Max output

50K

Input

Text

Text and Images

Output

Text

Reasoning

Shows its thinking

Answers directly

Knowledge cutoff

—

2024-03-31

Try it with real numbers

2K tokens in · 500 tokens out.

Mercury 2

Inception

0.1¢

for this task

57% input · 43% output

Full pricing →

MiniMax-01

MiniMax

0.11¢

for this task

42% input · 58% output

Full pricing →

All 2, same prompt and context: 0.21¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 2,382 of these.

Which should you pick?

For long documents, MiniMax-01 has the largest context window here — 1M tokens.

On price, Mercury 2 is the cheapest of the two on a typical task, at about 0.21¢.

For images or files, MiniMax-01 can read them directly; Mercury 2 is text-only.

If you want to watch the model think, Mercury 2 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 →

Mercury 2 pricing →MiniMax-01 pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Mercury 2 or MiniMax-01?

On a typical client proposal (5K tokens in, 800 out): Mercury 2 at 0.21¢; MiniMax-01 at 0.22¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

MiniMax-01 — 1M tokens, about 1,400 pages.

Can I run Mercury 2 and MiniMax-01 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 0.43¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 0.43¢ for a typical client proposal. Free to start, with $5 of credit.