█

AI/TLDR

Buy me a coffee
Buy me a coffee
PROMOTE YOUR WEBSITE IN JUST $20

Model comparison

Mistral Small 4 vs Mistral Small 3.2

Mistral AIMistral Small 4
Input
$0.15 / 1M tokens
Output
$0.60 / 1M tokens
Context
256K
Released
2026-03-16
Full model page →Mistral AIMistral Small 3.2
Input
$0.10
Output
$0.30
Context
128K
Released
2025-06-20
Full model page →
Short answer

Mistral Small 4 scores higher on 1 of the 1 benchmarks both models report; Mistral Small 3.2 is cheaper on input tokens ($0.1 vs $0.2 per 1M, 1.5×); Mistral Small 4 has the larger context window (256K vs 128K).

Specs and pricing side by side

SpecMistral Small 4Mistral Small 3.2
MakerMistral AIMistral AIsame
Released2026-03-162025-06-20
Context window256K128K
Input price$0.15 / 1M tokens$0.10
Output price$0.60 / 1M tokens$0.30
Parameters119B total / 6.5B active (MoE)24B
LicenseApache 2.0Apache 2.0same
WeightsOpen weightsOpen weightssame
ModalitiesText, VisionText, Visionsame
Knowledge cutoffNot disclosedOctober 2023

Not published by either maker: max output.

Benchmarks both models report

BenchmarkMistral Small 4Mistral Small 3.2
GPQA Diamond71.2%46.13%

Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.

Which one should you pick?

Pick Mistral Small 4 if…

  • You care about GPQA Diamond (it scores higher on 1 shared benchmark).
  • You need the longer context (256K vs 128K).
  • Your use case is: self-hosted assistants and agents where an open, commercially-usable license matters.

Pick Mistral Small 3.2 if…

  • Cost matters: input tokens cost 1.5× less ($0.1 vs $0.2 per 1M).
  • Your use case is: self-hosted chat assistants and internal copilots where data must stay on-premise.

FAQ

Which is better, Mistral Small 4 or Mistral Small 3.2?

Mistral Small 4 scores higher on 1 of the 1 benchmarks both models report; Mistral Small 3.2 is cheaper on input tokens ($0.1 vs $0.2 per 1M, 1.5×); Mistral Small 4 has the larger context window (256K vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.

How much cheaper is Mistral Small 3.2?

Mistral Small 4: $0.15 / 1M tokens input, $0.60 / 1M tokens output. Mistral Small 3.2: $0.10 input, $0.30 output (list API prices as published by each maker).

What are the context windows of Mistral Small 4 and Mistral Small 3.2?

Mistral Small 4 offers 256K; Mistral Small 3.2 offers 128K.

Is Mistral Small 4 newer than Mistral Small 3.2?

Mistral Small 4 was released 2026-03-16; Mistral Small 3.2 was released 2025-06-20.

Go deeper