Skip to main content

Quickstart

Make your first request through otari.ai in a few minutes. This is the shortest hosted path: you'll use your default workspace, generate a workspace token, send one request, and confirm it appears in the Usage tab.

What you need

Let's keep the first run small and just make sure the platform works.

  • An otari.ai account and access to a workspace

  • A new workspace token from the API Keys tab

Prefer self-hosting instead? Use the gateway deployment guide.

1. Open a workspace

Use your default workspace for the first request.

  1. Log in to otari.ai.

  2. Open your default workspace in the top-left corner.

  3. You will use the API Keys, Models, and Usage tabs in this guide.

About the workspace ID

Some SDK and CLI flows use the workspace ID, but you do not need it for the first API request on this page. If another guide asks for it later, you can copy it from the workspace URL or settings.

2. Generate an API token

Next, generate the credential your app will actually send to otari.ai. This token starts with otk_.

  1. Open the API Keys tab.

  2. Click Create Key.

  3. Give the key a name and, if needed, set an expiration date. By default, the key inherits your existing model access, but you can limit it to specific models. To customize model access, click Advanced and select the models you want the key to use.

  4. Copy the token right away. It is only shown once.

Treat this like a password. Keep it in your shell or secret store, not in source control.

3. Send your first request

Pick a model your workspace can use.

  1. Open the Models tab.

  2. Choose a model using the available filters, including modality, provider, vendor, capabilities, and more, to quickly find the option that best fits your needs.

  3. After selecting a model, click Use this model in the top-right corner.

otari.ai exposes an OpenAI-compatible endpoint at https://api.otari.ai/v1. The fastest first check is one cURL request that you can copy. The example uses deepseek/deepseek-v4-pro-0813.

curl https://api.otari.ai/v1/chat/completions \   
-H "Authorization: Bearer $OTARI_API_KEY" \   
-H "Content-Type: application/json" \
-d '{
     "model": "deepseek/deepseek-v4-pro-0813",
     "messages": [
          {
            "role": "user",
            "content": "Say hello in one short sentence."
           }
      ]
   }'

4. Confirm it worked

  1. Open the Usage tab.

  2. Look for the request you just sent.

  3. If it does not appear, double-check the provider key and workspace token first.

✔️ Success

Once the request appears in Usage, your hosted path is working. From there, you can add budgets, more providers, or an editor integration.

What to do next

Provider Keys: Go deeper on BYOK, provider access, and how keys are assigned to workspaces.
👉 Provider key guide

Budgets: Add spend controls once your first request is working and usage starts showing up.
👉 Budget guide

Integrations: Point Claude Code or OpenCode at otari.ai after you have a working API key and provider path.

👉 Claude Code & OpenCode

Did this answer your question?