Mistral AI

Mistral: Mistral Small 3.1 24B

by Mistral AItext+image->text1 endpoint

Overview

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
TextImage
Output
Text

Technical Specifications

Context Window
128K tokens
Max Output
102.4K tokens
Knowledge Cutoff
2023-10-31
Tokenizer
Mistral
Uptime (24h)
10000.0%

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_logprobstop_p

Pricing

Per 1M tokens
Input$0.35
Output$0.56
Added
March 17, 2025
Last synced 9/21/2026