Skip to main content

​
Welcome to orq.ai

This page covers the fastest way to create an initial deployment and make a first LLM call through the platform.

​
Prerequisite

An account within the orq.ai Studio is required.
Sign Up Here to create an orq.ai Account.

​
Step 1: Setup an API Key with the available providers

To start using models, first add an API key with the chosen provider. To do so, open the Model Garden > Providers tab, select a provider, and choose Setup own API Key.
Screenshot2025 11 03at14 44 14 Pn
Screenshot 2025-11-03 at 14.11.53.png
To learn more about setting up Integrations, see API keys & Endpoints.

​
Step 2: Enable models in the Model Garden

Browse the Model Garden by going to the Model Garden tab. Here, find all models available to use within orq.ai, including their capabilities and a short description. To make any model available, toggle the button next to its name, it will then be usable in a first Deployment. To use custom API keys, head to the Integration tab.
To learn more about all the models available, see Model Garden.

​
Step 3: Set up a first Deployment

To create a first deployment, head to the Deployment tab, then select Create Deployment.
The Variant configuration screen will then appear. Here, select which parameters to use with the model and include the prompt(s) that will be sent to the language model.
Once ready, press the Deploy button at the top-right to save the latest configuration and make it available through the API.
There are many more features available to configure a Deployment. Including setting up multiple models, fallbacks, function calling, etc. To learn more, see Creating a Deployment.

​
Step 4: Install the orq.ai SDK

Within the Deployment page, open the code snippet panel to find instructions to install and run the SDK for the current deployment.
Then, proceed to install the chosen SDK. Execute the following in a terminal to download the latest version of the SDK on the machine. 
npm install @orq-ai/node --save

​
Step 5: Get an API Token

An API key is needed to set up the client. This can be found within the Workspace Settings > API Keys menu.
To learn more about API Authentication, see Authentication.

​
Step 6: Use the SDK to invoke a Deployment

Once the API Token has been saved for use, refer back to the code snippet accessed before the Deployment to fetch the code to initialize and invoke a deployment:
Don’t forget to replace <API_KEY> with the API key fetched previously. 
import { Orq } from "@orq-ai/node";

const client = new Orq({
  apiKey: '<API_KEY>',
  environment: 'production',
});

const deployment = await client.deployments.invoke({
   key: "quickstart-deployment",
   context: {
      environments: []
   },
   metadata: {
      "custom-field-name": "custom-metadata-value"
   }
});
Congratulations, the first deployment invocation with orq.ai was successfully run. To learn more about deployments and all the possibilities they offer, see Creating a Deployment.

​
Step 7: Track projects and costs

orq.ai allows tracking costs and projects grouped in Contacts. Use a Contact within any SDK before invoking a generation to log all usage within that contact.
Contacts can also be created using the SDK. See how with the Node SDK and Python SDK. 
import { Orq } from "@orq-ai/node";

const client = new Orq({
  apiKey: '<API_KEY>',
  environment: 'production',
  contactId: '<contact-id>'
});

const deployment = await client.deployments.invoke({
   key: "quickstart-deployment",
   context: {
      environments: []
   },
   metadata: {
      "custom-field-name": "custom-metadata-value"
   }
});
To learn more about Contacts and the resulting Analytics, see Using Contact Metrics.