---
name: Mistral-Small-2503
slug: small-2503
type: Multimodal
providers:
  - cortecs
description: >-
  Combines advanced text and vision capabilities with 24 billion parameters,
  supporting multilingual tasks and long contexts up to 131k tokens, making it
  versatile for various applications without sacrificing performance.
tags:
  - tool-use
  - multimodal
is_open_source: false
context_window: 128000
max_output: 128000
pricing:
  - image: 0
    input: 0.111
    output: 0.334
    provider: cortecs (Ver 2503)
release_date: '2025-03-20'
capabilities:
  audio: false
  vision: true
  tool_use: true
  citations: false
  reasoning: false
---
Mistral-Small-2503 is a Multimodal model.
Combines advanced text and vision capabilities with 24 billion parameters, supporting multilingual tasks and long contexts up to 131k tokens, making it versatile for various applications without sacrificing performance.