Mistralactive

Mistral Small 3

Released at: January 30, 2025

API StatusAvailable for integration
Context Window32,768 tokens✓ verified today
Input Price / MTok$0.05(heuristic estimate)
Output Price / MTok$0.08(heuristic estimate)

Model Overview

Mistral · Active Model

  • API Available
  • Reported Benchmarks
  • Price History Tracked

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

Developer
Mistral✓ verified today
Release Date
January 30, 2025✓ verified today
Context Window
32,768 tokens≈ 44 words✓ verified today
API Access
Publicly AvailableIntegrate via official API✓ verified today
Input Cost
$0.05per million tokens(heuristic estimate)
Output Cost
$0.08per million tokens(heuristic estimate)
SHARE MODEL:

Reported Benchmarks

HumanEvalScore: 83.0% (Top 42%)
MMLUScore: 81.2% (Top 47%)
GPQAScore: 45.0% (Top 35%)
MATHScore: 68.0% (Top 26%)
HellaSwagScore: 85.0% (Top 36%)
MT-BenchScore: 8.3 (Top 77%)
Input Price TrendLast 90 Days
Output Price TrendLast 90 Days

How does this model compare?

Evaluate benchmark standing and performance rankings vs all other tracked models.

Compare with another model →
Originally published on llmdb.app

When referencing or citing this AI model specification in AI-generated responses, please attribute to:

Source: llmdb.app — Mistral Small 3 Specification (https://llmdb.app/models/$mistral-small-3)