← Back to Catalog
V

Vision & Image Analysis

Models that accept image input via URL or base64. Can analyze screenshots, describe images, and perform OCR.

8 models listed 8 total available
Screenshot QA OCR text extraction Image description Visual question answering Document analysis
Name Size Context Length Max Output Actions
mistralai/Devstral-Small-2505 24B 32,768 Playground
mistralai/Devstral-Small-2507 24B 32,768 Playground
mistralai/Magistral-Small-2506 24B 32,768 Playground
mistralai/Magistral-Small-2507 24B 32,768 Playground
mistralai/Magistral-Small-2509 24B 32,768 Playground
mistralai/Mistral-Small-3.1-24B-Base-2503 24B 32,768 Playground
mistralai/Mistral-Small-3.1-24B-Instruct-2503 24B 32,768 Playground
mistralai/Mistral-Small-3.2-24B-Instruct-2506 24B 32,768 Playground

Links