AI Hub
All models
MultimodalOpen weights

Mistral Small 3.1 24B Base

Mistral AI

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
Multimodal
Access
Open weights
Released
March 17, 2025
License
apache 2 0
Parameters
24000000000
Context window
128,000 tokens
Output speed
137 tok/s
Latency (TTFT)
0.23s
API pricing
$0.10 in · $0.30 out / 1M tokens
Capabilities
Function callingStructured output

Benchmarks

Reasoning

Multimodal

MMMU
59.3

General

Compare Mistral Small 3.1 24B Base with

See all Mistral Small 3.1 24B Base alternatives →