Tool detail

Mistral AI · Moderation

Classifies input text into policy-violating content categories, such as hate, violence, or sexual content, using a Mistral moderation model.

Categories: Text processing, LLM inference

Use when

check whether a piece of text violates content policy
screen user-generated text for unsafe content categories
flag messages that contain hateful or violent content

Not for

not for generating or rewriting text (see Chat Completion)

Inputs

inputs undocumented

Inputs undocumented: mpp.dev lists no input schema; see the provider's API reference

Endpoint

Method: POST
URL: https://mistral.mpp.paywithlocus.com/mistral/moderate

Payment

Protocol: MPP
Listed price: 0.008 of asset 0x20c000000000000000000000b9537d11c60e8b50 (6dp) per request on tempo:mainnet
Payment method: tempo
Network: tempo:mainnet
Asset: 0x20c000000000000000000000b9537d11c60e8b50

Listed terms are catalog metadata. The caller supplies inputs and calls the tool outside Onelayer. If payment is required, the caller uses a compatible wallet to pay.

Source

Directory: MPP directory
Record: mistral POST /mistral/moderate
Retrieved: 2026-09-30T20:37:07.382Z
Catalog file SHA-256: 6837ccddf886f0007cf3727ea9d27faaa5047b51b4f425345c554ce1c271a524
Catalog built: 2026-09-30T22:31:58.034Z