Skip to main content

​
What are Cost Policies?

Cost policies let you set spending limits and budget controls for AI usage across your organization. Define monthly budgets per application, per user, or per team to prevent unexpected costs and ensure fair resource allocation. Dashboard: gateway.getunbound.ai/policies/cost-policies

​
Cost Controls

​
Application Budgets

Set a monthly spending limit for each application. When the budget is reached, requests are either blocked or routed to more cost-effective models depending on your configuration.
  • Monthly Budget — Maximum spend per calendar month
  • Budget Action — Block requests or downgrade to cheaper models when limit is reached

​
Model Cost Optimization

Use model policies to route requests to cost-effective models by default, while keeping expensive models available for complex tasks:
  • Route simple completions to smaller, cheaper models
  • Reserve premium models for tasks that require higher capability
  • Use sensitivity-based routing to only send sensitive data to private (often more expensive) models

​
Usage Monitoring

Track costs in real-time from the Unbound dashboard:
  • Per-user breakdown — See which team members consume the most resources
  • Per-model costs — Understand spending across different LLM providers
  • Trend analysis — Identify usage patterns and optimize accordingly

​
Setting Up Cost Policies

  1. Go to Cost Policies in the Unbound dashboard
  2. Set budget limits and cost controls
  3. Configure model routing rules to optimize costs (see Model Policies)

​
Applying to Users

Cost policies can be attached to user groups to control which users are affected. Go to User Groups to create groups and assign cost policies to them.

​
Managing via CLI

List and manage cost policies from the terminal: 
unbound policy list --type COST
unbound policy get <policy-id>

Model Policies

Configure model routing to optimize costs

Tool Policies

Monitor terminal commands and MCP tool calls