Magistral Small 1.2

by Mistral

Small multimodal reasoning model (Sep 2025)

ReasoningVisionToolsStructured output

Context window

128K

Max output

Input price

$0.50 /1M

Output price

$1.50 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#270 of 505 LLMs

TierEfficient

Output speed113 tok/s

First token0.37s

Intelligence Index18.2

Coding Index14.8

Math Index80.3

MMLU-Pro

77%

GPQA Diamond

66%

Humanity's Last Exam

LiveCodeBench

72%

SciCode

35%

AIME 2025

80%

IFBench

44%

Long-context reasoning

16%

Terminal-Bench Hard

τ²-Bench Telecom

28%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Available routes

The same Magistral Small 1.2 runs on 1 route through the Opper gateway. Each route has its own data-handling posture.

Provider	Region	Zero data retention	Training	Logging	Contract	Input	Output
Mistral	EU	Opt-in	No (opt-in)	Up to 30 days for abuse monitoring	PAYG	$0.50	$1.50

Human review: Abuse-flagged only

Other models from Mistral