Define usage limits and provider/model access for a group of roles.
Before you start
The Manage AI Settings right.
Steps
- Go to Settings → Artificial Intelligence → Security Models.
- Click Add Policy.
- Fill in:
- Name and Description.
- Max Tokens Per Request (default 4096), Max Context Length (default 128000).
- Max Tokens Per Day (default 100000), Max Requests Per Day (default 100).
- Allowed Providers and Allowed Models — leave empty to allow all, or restrict to specific ones.
- Allow Image Upload and Allow MCP Tools toggles.
- Assigned Roles — which Security Roles this policy applies to.
- Save.
Related articles
Other guides that answer questions close to this one.
AI Security Models Explained
Naming note: despite sharing the name "Security Model," this is unrelated to the Branch Types / Security Models feature under My Account (Workspace) — that one governs sub-organizations; this one governs AI access…
AI Providers Explained
An AI provider is a connection to a model vendor — OpenAI, Anthropic, Google (Gemini), Mistral, Cohere, OpenRouter, DeepSeek, xAI (Grok), Meta (Llama), Perplexity, Hugging Face, or a Custom OpenAI-compatible endpoint.…
MCP Servers Explained
An MCP (Model Context Protocol) server gives the AI access to external tools — a standardized way for an AI model to call out to a tool or data source beyond its own training, rather than every integration needing…