← Back to hard AIs

Verify critical details — pricing, licensing, availability — with the model's source before business decisions. Full methodology →

Models · Mistral AI

Mistral Moderation

Model family: safety

Mistral's content-moderation classifier — nine harm categories, multilingual, closed-APIA model that's only accessible through the creator's own API or product — you can't download it, run it yourself, or inspect its weights. GPT-4, Claude, and Gemini Pro are closed-API models. The tradeoff is convenience and often capability (closed-API models are frequently the strongest) versus loss of control over data, pricing, and availability. at $0.10 per million tokens.

Identity

Creator
Mistral AI
Model family
safety
Release date
2024-11-07

Technical specs

Parameter count
Mistral has not published parameter counts. Moderation classifiers are typically small (hundreds of millions of parameters) optimized for fast inference and high throughput at classification tasks.
Context window
8.2K tokens
Modalities
  • Text
Primary capabilities
  • Classification
  • Multilingual

License

License
Mistral AI Terms of Service (Proprietary API)
Commercial use
  • Allowed
Terms
  • Modification
  • Redistribution
  • Attribution

Access

Openness
  • Closed Api
Access methods
  • Api First Party
  • Api Third Party
Cost tier
  • Paid Api
Cost details
  • API input: $0.10 / 1M tokens
  • $0.10 per million tokens for moderation classification. Returns probabilistic scores across nine harm categories per input.

Full model card →