Policies | AI Router

Bundle model routing, evaluators, and budget limits into named AI Router policies that you invoke directly from your API calls.

Feature available with the Enterprise Plan

Policies are the highest-level routing control in the AI Router. A policy bundles model routing, evaluators, and budget limits into a single named configuration that can be invoked directly from your API calls.

Use cases

Policies are most useful when you need to enforce consistent model access, compliance checks, and spend limits across a team or project from a single place.

Enforce workspace-wide safety with a spending cap

A global policy that routes all workspace traffic through a single approved model, runs a safety Evaluator on requests, and enforces a token limit to cap spend across every project.

Detect PII on EU document workloads

Routes EU document workloads to a designated model and samples every request through a PII Evaluator to detect sensitive data before it reaches the model.

Lock a testing environment to a cheaper model with GDPR checks

Scopes a policy to the testing environment, locks it to a cost-effective model, attaches a medical advice Evaluator, and caps traffic at 1000 requests per minute so test workloads never exceed approved spend.

Keep costs down across all projects

A global policy that attaches a quality Evaluator and enforces request and token limits, so quality is checked and spend stays controlled across all projects.

Enforce US PII compliance in production

Runs a US-specific PII Evaluator on all production traffic from a single policy.

Give a support team access to approved models within a budget

Scopes the support project to a specific model, attaches a cost Evaluator, and enforces a monthly budget limit so the team can only use what has been approved.

How policies work

Policies sit at the top of the routing hierarchy:

• When a policy with a model configured is matched, Routing Rules are bypassed.
• If the policy has no model configured, the router falls back to Routing Rules and applies the highest-priority matching rule.
• Any Guardrail Rules that match the request are still evaluated and enforced, regardless of which policy is active.

Visibility

• Global policies: visible to workspace administrators only.
• Project policies: visible to all members of the scoped project.

Creating a policy

From the Policies list, click Add New Policy. A panel opens on the right with the following fields.

General

Field	Description
Policy Name	A display name for the policy. Used as the identifier when invoking the policy in code.
Description	Optional context for other administrators.
Enable Policy	Toggle to activate or deactivate the policy without deleting it.
Project	Scope of the policy. Global (all projects) applies the policy workspace-wide. Selecting a specific project restricts the policy to calls made within that project, and only entities belonging to that project are evaluated.

Providers and traffic weight

Defines which models handle traffic and how requests are distributed across them.

Models sets the distribution strategy:

• Fallback: Requests go to the primary model. If it fails, the next model in the list is tried.
• Weighted: Traffic is split across models by percentage weights you assign.
• Round Robin: Requests rotate evenly across all configured models.

Click Add to add a model to the policy.

Evaluators

Attach one or more Evaluators to gate requests through the policy. Click Add to select from the evaluators available in the scoped project. Each evaluator has a configurable Sample Rate: the percentage of requests that are evaluated. Unlike Guardrail Rules, evaluators attached to a policy are not condition-triggered. They run on every sampled request.

Execution settings

Field	Description
Timeout	Maximum time in seconds allowed for the entire policy to complete. If the timeout is reached, the policy execution stops.
Retries	Number of times the policy retries on failure before giving up.

Budget

The Budget section contains three independently toggleable limits. Each has a configurable period: Hourly, Daily, Weekly, or Monthly.

Limit	Field	Description
Max spend	Amount in USD	Maximum dollar spend per period.
Token limit	Max tokens	Maximum number of tokens consumed per period.
Request limit	Max requests	Maximum number of API requests per period.

Each limit can be enabled or disabled individually. The next to the period selector clears the current value.

Invoking a policy

Reference a policy in your API call using policy/<policy-name> as the model value. The name must match the Policy Name you set when creating the policy.

TypeScript

import { OpenAI } from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.orq.ai/v3/router',
  apiKey: process.env.ORQ_API_KEY,
});

const completion = await openai.chat.completions.create({
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What can you help me with today?' },
  ],
  model: 'policy/mypolicy',
});

console.log(completion.choices[0]);

Replace mypolicy with the name of your policy.