Mistral Moderation 2

mistral/mistral-moderation-2603

Mistral Moderation 2 (March 2026), Mistral's API classifier that scores text or conversations across 11 categories, from hate and self-harm to PII, adds jailbreak detection and reads up to 128K tokens; it replaced the 2024 moderation model.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/moderations" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral/mistral-moderation-2603",
  "input": "Hello, world."
}'

Input Price: $0.00 / request
Output Price: —
Input: Text
Output: Classification

Capabilities

Explore what Mistral Moderation 2 supports, then use the API section for a request tailored to this model.

Model Information

Provider: Mistral AI
Product: Moderation
Release Date: Mar 2026
Data Policy: Configurable
Region: Global
Input: Text
Output: Classification

Provider Documentation

Playground

Try Mistral Moderation 2 by Mistral AI. Requests use the selected workspace’s credits and API pricing.

Mistral Moderation 2

This model uses a dedicated input format. Explore its API example or open the supported playground.

View API reference

Providers

Compare available endpoints, pricing, and context limits for Mistral Moderation 2.

Provider	Context	Output	Input Price	Output Price	Endpoint
Mistral AI	Not specified	Classification	$0.00 / request	—	`mistral-moderation-2603`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max input bytes	16384
Max batch	1

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/moderations" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral/mistral-moderation-2603",
  "input": "Hello, world."
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`mistral/mistral-moderation-2603` — Required model identifier.
`input`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max input bytes	16384
Max batch	1

Similar Models

Explore more moderation and compare their capabilities.

Model	Context	Input Price	Output Price
Omni ModerationOpenAI	Not specified	$0.00 / request	—

View All Moderation