All models

Gemini 2.5 Pro Preview 05-06 vs Mistral Medium 3.5

Gemini 2.5 Pro Preview 05-06 at $1.44 in and $11.50 out and Mistral Medium 3.5 at $1.73 in and $8.63 out — per million tokens, from the same wallet.

Gemini 2.5 Pro Preview 05-06

Google

1.6¢

for a client proposal

$1.44 in · $11.50 out / 1M

1.05M context · released May 2025

Full page →
M

Mistral Medium 3.5

Mistral AI

1.6¢

for a client proposal

$1.73 in · $8.63 out / 1M

262K context · released 6 months ago

Full page →

Asking all both at once — identical prompt, identical context — costs about 3.2¢ for a typical client proposal.

At a glance

  • Cheapest input: Gemini 2.5 Pro Preview 05-06 at $1.44 per million tokens.
  • Cheapest output: Mistral Medium 3.5 at $8.63 per million tokens.
  • Largest context: Gemini 2.5 Pro Preview 05-06 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
Gemini 2.5 Pro Preview 05-06
0.86¢
Mistral Medium 3.5
0.78¢

Draft a client proposal from notes

5K in · 800 out
Gemini 2.5 Pro Preview 05-06
1.6¢
Mistral Medium 3.5
1.6¢

Context-heavy session (Alyph workspace)

155K in · 4K out
Gemini 2.5 Pro Preview 05-06
$0.27
Mistral Medium 3.5
$0.30

Analyze a 50-page legal contract

35K in · 1K out
Gemini 2.5 Pro Preview 05-06
$0.06
Mistral Medium 3.5
$0.07

Large architecture refactor

250K in · 3K out
Gemini 2.5 Pro Preview 05-06
$0.77
Mistral Medium 3.5
$0.46

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
free$2.87$5.750 tokens250k500k750k1000k
Gemini 2.5 Pro Preview 05-06
Mistral Medium 3.5

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

Pricing

Gemini 2.5 Pro Preview 05-06
Mistral Medium 3.5
Input / 1M tokens
$1.44
$1.73
Output / 1M tokens
$11.50
$8.63
Cached input / 1M
$0.144
—
Web search
1.6¢ / search
—

Specs

Gemini 2.5 Pro Preview 05-06
Mistral Medium 3.5
Released
May 2025
6 months ago
Context window
1.05M
262K
Max output
66K
—
Input
Text, Images, Files, Audio, and Video
Text, Images, and Files
Output
Text
Text
Reasoning
Shows its thinking
Shows its thinking
Knowledge cutoff
2025-01-31
—

Try it with real numbers

2K tokens in · 500 tokens out.

Gemini 2.5 Pro Preview 05-06

Google

0.86¢

for this task

33% input · 67% output

Full pricing →

Mistral Medium 3.5

Mistral AI

0.78¢

for this task

44% input · 56% output

Full pricing →

All 2, same prompt and context: 1.6¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 305 of these.

Which should you pick?

For long documents, Gemini 2.5 Pro Preview 05-06 has the largest context window here — 1.05M tokens.

On price, Mistral Medium 3.5 is the cheapest of the two on a typical task, at about 1.6¢.

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 →

Questions, answered

Which is cheaper, Gemini 2.5 Pro Preview 05-06 or Mistral Medium 3.5?

On a typical client proposal (5K tokens in, 800 out): Mistral Medium 3.5 at 1.6¢; Gemini 2.5 Pro Preview 05-06 at 1.6¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

Gemini 2.5 Pro Preview 05-06 — 1.05M tokens, about 1,500 pages.

Can I run Gemini 2.5 Pro Preview 05-06 and Mistral Medium 3.5 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 3.2¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 3.2¢ for a typical client proposal. Free to start, with $5 of credit.