Mistral Small 3 vs gpt-oss-120b

Mistral Small 3 at $0.058 in and $0.092 out and gpt-oss-120b at $0.043 in and $0.196 out — per million tokens, from the same wallet.

Mistral Small 3

Mistral AI

0.04¢

for a client proposal

$0.058 in · $0.092 out / 1M

33K context · released January 2025

Full page →

gpt-oss-120b

OpenAI

0.04¢

for a client proposal

$0.043 in · $0.196 out / 1M

131K context · released August 2025

Full page →

Asking all both at once — identical prompt, identical context — costs about 0.07¢ for a typical client proposal.

At a glance

Cheapest input: gpt-oss-120b at $0.043 per million tokens.
Cheapest output: Mistral Small 3 at $0.092 per million tokens.
Largest context: gpt-oss-120b at 131K tokens — about 190 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

Mistral Small 3

0.02¢

gpt-oss-120b

0.02¢

Draft a client proposal from notes

5K in · 800 out

Mistral Small 3

0.04¢

gpt-oss-120b

0.04¢

Context-heavy session (Alyph workspace)

155K in · 4K out

Mistral Small 3

needs 155K ctx

gpt-oss-120b

needs 155K ctx

Analyze a 50-page legal contract

35K in · 1K out

Mistral Small 3

needs 35K ctx

gpt-oss-120b

0.17¢

Large architecture refactor

250K in · 3K out

Mistral Small 3

needs 250K ctx

gpt-oss-120b

needs 250K ctx

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

Mistral Small 3

gpt-oss-120b

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

Pricing

Mistral Small 3

gpt-oss-120b

Input / 1M tokens

$0.058

$0.043

Output / 1M tokens

$0.092

$0.196

Specs

Mistral Small 3

gpt-oss-120b

Provider

Mistral AI

OpenAI

Released

January 2025

August 2025

Context window

33K

131K

Max output

16K

131K

Input

Text

Output

Text

Reasoning

Answers directly

Shows its thinking

Knowledge cutoff

2023-10-31

2024-06-30

Try it with real numbers

2K tokens in · 500 tokens out.

Mistral Small 3

Mistral AI

0.02¢

for this task

71% input · 29% output

Full pricing →

gpt-oss-120b

OpenAI

0.02¢

for this task

47% input · 53% output

Full pricing →

All 2, same prompt and context: 0.03¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 14,541 of these.

Which should you pick?

For long documents, gpt-oss-120b has the largest context window here — 131K tokens.

On price, Mistral Small 3 is the cheapest of the two on a typical task, at about 0.04¢.

If you want to watch the model think, gpt-oss-120b 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 →

Mistral Small 3 pricing →gpt-oss-120b pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Mistral Small 3 or gpt-oss-120b?

On a typical client proposal (5K tokens in, 800 out): Mistral Small 3 at 0.04¢; gpt-oss-120b at 0.04¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

gpt-oss-120b — 131K tokens, about 190 pages.

Can I run Mistral Small 3 and gpt-oss-120b 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 0.07¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 0.07¢ for a typical client proposal. Free to start, with $5 of credit.