Command R (08-2024) vs Mistral Small 4

Command R (08-2024) at $0.172 in and $0.690 out and Mistral Small 4 at $0.172 in and $0.690 out — per million tokens, from the same wallet.

Command R (08-2024)

Cohere

0.14¢

for a client proposal

$0.172 in · $0.690 out / 1M

128K context · released August 2024

Full page →

Mistral Small 4

Mistral AI

0.14¢

for a client proposal

$0.172 in · $0.690 out / 1M

262K context · released 5 months ago

Full page →

Asking all both at once — identical prompt, identical context — costs about 0.28¢ for a typical client proposal.

At a glance

All 2 cost the same on input.
Largest context: Mistral Small 4 at 262K tokens — about 370 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

Command R (08-2024)

0.07¢

Mistral Small 4

0.07¢

Draft a client proposal from notes

5K in · 800 out

Command R (08-2024)

0.14¢

Mistral Small 4

0.14¢

Context-heavy session (Alyph workspace)

155K in · 4K out

Command R (08-2024)

needs 155K ctx

Mistral Small 4

2.9¢

Analyze a 50-page legal contract

35K in · 1K out

Command R (08-2024)

0.67¢

Mistral Small 4

0.67¢

Large architecture refactor

250K in · 3K out

Command R (08-2024)

needs 250K ctx

Mistral Small 4

4.5¢

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

Command R (08-2024)

Mistral Small 4

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

Pricing

Command R (08-2024)

Mistral Small 4

Input / 1M tokens

$0.172

Output / 1M tokens

$0.690

Cached input / 1M

—

$0.017

Specs

Command R (08-2024)

Mistral Small 4

Provider

Cohere

Mistral AI

Released

August 2024

5 months ago

Context window

128K

262K

Max output

—

Input

Text

Text and Images

Output

Text

Reasoning

Answers directly

Shows its thinking

Knowledge cutoff

2024-03-31

—

Try it with real numbers

2K tokens in · 500 tokens out.

Command R (08-2024)

Cohere

0.07¢

for this task

50% input · 50% output

Full pricing →

Mistral Small 4

Mistral AI

0.07¢

for this task

50% input · 50% output

Full pricing →

All 2, same prompt and context: 0.14¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 3,623 of these.

Which should you pick?

For long documents, Mistral Small 4 has the largest context window here — 262K tokens.

On price they are identical: about 0.14¢ for a typical task each.

For images or files, Mistral Small 4 can read them directly; Command R (08-2024) is text-only.

If you want to watch the model think, Mistral Small 4 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 →

Command R (08-2024) pricing →Mistral Small 4 pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Command R (08-2024) or Mistral Small 4?

On a typical client proposal (5K tokens in, 800 out) they cost the same — about 0.14¢ each. Compare them on context and capabilities instead.

Which has the largest context window?

Mistral Small 4 — 262K tokens, about 370 pages.

Can I run Command R (08-2024) and Mistral Small 4 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 0.28¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 0.28¢ for a typical client proposal. Free to start, with $5 of credit.