Last updated: 16/04/2025

MistralOfficial Docs

Mistral Moderation

mistral-moderation-latest

active

Mistral Moderation

Mistral Moderation is a powerful text content moderation classifier service that helps maintain safe and appropriate online environments. With a large 32,768 token context window, it can handle a wide range of text-based inputs and outputs, including text, image, video, audio, transcription, and text-to-speech.

Supports fine-tuning for customized applications, allowing teams to adapt the model to their specific domain needs while maintaining performance and reliability.

Additional Information

Notes

Currently points to mistral-moderation-2411. Has a context length of 32768 tokens. Also has the alias mistral-moderation-2411.

Model Timeline

Last Updated

11/1/2024

Capabilities

Text

Input Pricing

$0.00/ KTok

Context: 32,768 tokens

Output Pricing

$0.00/ KTok

Embeddings

Embeddings Pricing

$0.10/1k tokens

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop