Mistral AI content moderation via pay-per-call MPP on Tempo L2
What it does
This endpoint provides access to Mistral AI's content moderation API through the Locus MPP (Micropayment Protocol) gateway. It accepts text input and classifies it using Mistral's moderation model (e.g. "mistral-moderation-latest"), returning category-level safety assessments. Payment is settled per-call on Tempo L2 using pathUSD.
The endpoint is part of a broader Mistral AI service suite hosted on the same Locus MPP gateway, which also offers chat completions, embeddings, and model listing. The moderation endpoint specifically charges 8,000 base units of pathUSD (6 decimals), which works out to $0.008 per request. The request body requires a `model` string and an `input` string (or array of strings) to moderate.
Note that the probe returned 404 on HEAD and GET — this is expected because the endpoint only accepts POST requests, as defined in the OpenAPI spec. The OpenAPI schema is well-structured and includes payment metadata, request schemas, and endpoint descriptions. However, no response schema is documented, and no example responses are available from the crawl. The upstream Mistral moderation API documentation at docs.mistral.ai would provide additional detail on response format and supported moderation categories.
Capabilities
Use cases
- —Screening user-generated content for policy violations before publishing
- —Automated content moderation pipelines for chat or forum platforms
- —Pre-filtering LLM outputs for safety before returning to end users
- —Compliance checks on text submissions in regulated environments
Fit
Best for
- —Agents needing pay-per-call content moderation without API key management
- —Automated safety screening of text at low per-request cost
- —Integrating moderation into crypto-native or MPP-based workflows
Not for
- —Image or video moderation (text-only endpoint)
- —High-volume moderation where per-call pricing may not be cost-effective compared to subscription plans
Quick start
curl -X POST https://mistral.mpp.paywithlocus.com/mistral/moderate \
-H "Content-Type: application/json" \
-d '{"model": "mistral-moderation-latest", "input": "I want to harm someone"}'Example
Request
{
"input": "I want to harm someone",
"model": "mistral-moderation-latest"
}Endpoint
Quality
The OpenAPI spec provides a clear request schema and payment metadata, but no response schema or example responses are available. The probe returned 404 because it used HEAD/GET on a POST-only endpoint, so liveness is not confirmed but is plausible. Crawl pages returned no useful documentation beyond error messages pointing to external docs.
Warnings
- —Endpoint liveness not directly confirmed — probe used HEAD/GET but endpoint only accepts POST
- —No response schema documented; response format must be inferred from upstream Mistral moderation API docs
- —No example responses available from crawl or OpenAPI spec
- —Currency address 0x20c000000000000000000000b9537d11c60e8b50 assumed to be pathUSD with 6 decimals based on Tempo L2 convention
Citations
- —The moderation endpoint charges 8000 base units via Tempo method with the listed currency addresshttps://mistral.mpp.paywithlocus.com
- —Request body requires model and input fieldshttps://mistral.mpp.paywithlocus.com
- —Upstream API reference available at docs.mistral.aihttps://mistral.mpp.paywithlocus.com
- —Additional Locus MPP documentation at paywithlocus.com/skill.md and paywithlocus.com/llms.txthttps://mistral.mpp.paywithlocus.com