ModelsCompareBest forBenchmarksStatusPricingAPI

Mistral Small 4

Mistral AI·Operational·Released 2026-03-16textvision
Context256k
Max output-
Input / 1M$0.15 ↗
Output / 1M$0.6 ↗
Cached in$0.015
Benchmarks3

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

Artificial Analysis Long Context Reasoning0.72 ↗
GPQA Diamond#52/7071.2% ↗
MMLU-Pro#19/2978% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Mistral AI

Mistral Medium 3.5Mistral Large 3CodestralMinistral 3 14BMinistral 3 8BMinistral 3 3B

Access Mistral Small 4 and every other model through one endpoint with automatic failover: Respan gateway.