Skip to main content

Quick Start

Updated on 16 November 2026.

Create an app, configure your SDK to use the gateway, and send a first request.

Create App
Name and key settings
Providers and models
Default guardrails applied
Copy the Quilr key
Shown after Create app
Also in API Integration
Swap the base URL
base_url → guardrails-usa-2.quilr.ai
api_key → Quilr key
SDK code: unchanged ✓
Check Activity
Outcome, tokens, latency
Cost per model
QuilrAI

Before you start​

You need one of:

  • Credentials for a provider (for example an OpenAI API key), or
  • A platform provider already set up in Settings > AI Gateway > Models (V2 console only, see Providers and Models). You can also add one from inside Create App.

1. Create the app​

Go to Settings > AI Gateway > LLM Gateway and click Create App. The wizard has two steps.

Step 1: Application and providers​

FieldNotes
Application nameRequired. 4 to 29 characters.
Application URLOptional.
Quilr key nameUnder Key settings (collapsed by default, showing Default · never expires). Required. Defaults to Default. Names the gateway key, not your provider key.
Initial key expiryUnder Key settings. Optional. Leave blank for a key that never expires.

Next, under Where should this app get its models?, choose where the provider credentials come from.

OptionUse it when
Platform providers (Recommended)You want this app to reuse providers your team already connected, with credentials and models managed in one place.
App-only credentialsYou want to enter provider credentials for this app only, for example when one team's keys must stay separate.
V2 console only

The Platform providers option exists only in the V2 console, and it is the default. In V1, every app keeps its own provider credentials. Either way, the choice is fixed once the app is created.

Platform providers. Under Available, tick one or more providers. The first one you tick is the Primary; use the up and down arrows to change the order. A disabled provider is skipped, and when the primary fails the gateway fails over to the next provider in the order (see When a provider fails). The app inherits all their models and credentials, including models added later. If none exist yet, click Add a platform provider to add one without leaving the form, or Use app-only credentials.

App-only credentials. Select App-only credentials and select a provider tile. For providers with more than one API, also select one under Which API does the gateway talk to?.

  1. Keep or change the Provider label.
  2. Fill in the credential fields. Each provider's fields are listed in Provider Support.
  3. Under Models, click Get available models and choose from the list, or type a model in Add a model by name and click Add. Each model is checked against the provider before it is added.
  4. Optional: click Add another provider to add more providers for routing.

Use QuilrAI-provided models

To connect an app to QuilrAI-provided models, add a Custom endpoint provider with the Chat completions API (general), base URL https://models.quilrai.dev/v1 and a model API key from Settings > AI Gateway > Models > API keys.

Click Create app. There is no guardrail step. New apps have the following classic settings, which you can change in Security Guardrails. When the Policy Engine is enabled, published policies decide the effective protection instead.

SettingDefault
Default guardrail actionMonitor. You can change it later to Block, Redact, Partial redact or Tokenize.
Data risksAll six on: PII, PHI, financial, payment card, insurance, authentication secrets
Adversarial risks12 of 13 on. Malicious scripts is off.
Dependency security check, Latest-version suggestions, Task adherenceOff. These are Guardian Agent checks.

Monitor logs detections without changing traffic.

Step 2: Key details​

The last step, Integration, shows the new Quilr key, the app's log export key and, if you have access, the all-apps log key. Copy them now, then click Done. You can copy the Quilr key again later from the app's API Integration section (see Applications and Keys).

2. Send your first request​

Point your client at a regional gateway URL and use the Quilr key. Nothing else changes.

from openai import OpenAI

client = OpenAI(
base_url='https://guardrails-usa-2.quilr.ai/openai_compatible/',
api_key='sk-quilr-xxx', # your Quilr key
)

resp = client.chat.completions.create(
model='gpt-4.1-mini', # a model enabled on the app
messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(resp.choices[0].message.content)

The example uses US East; replace the host with the regional host your organization uses. Select the appropriate path for your SDK (Anthropic, boto3, Vertex AI, Responses, Realtime), in the Integration Guide.

3. Check that it worked​

On the app card, click Logs. The Activity > Requests view lists each call with its model, provider, guardrail outcome, HTTP status, tokens and latency. See Overview for the operational views.

For the bigger picture, select Overall analytics to open LLM Gateway Insights. Its six tabs cover usage, agents and tools, performance, security, attachments and users. See Analytics and insights.

4. Tune the app​

Providers, keys and app-specific definitions remain on the app card's Configure actions. Choose the configuration mode that governs traffic for the controls below.

With the engine on, open Govern > Policy Engine > LLM Gateway. Choose the relevant control, select a recipe or start a blank rule, and scope it to your application. Save the rule to the shared draft, test it, then Review & publish.

Start with Security guardrails, Gateway access and allowed models, Routing and failover, or Budgets and limits. Editing classic settings does not change policy-governed traffic. See Author, simulate and publish for the complete workflow.