Skip to main content
Model API answers chat completions requests in the OpenAI format. This quickstart creates an API key, sends a first request with cURL or the OpenAI SDK, and shows where the console reports token usage.
Requests are paid from the team balance. Before the first request, sign in to the console and check on Billing Overview that the balance covers it.

Run a first request

1

Create an API key

Open API Keys in the console and select Add New Key.
Copy the key when it is created. The console does not show it again.
2

Store the key in an environment variable

The examples read the key from PPIO_API_KEY. Set the variable in the shell that runs the request.
3

Run the example

The example sends a chat completions request to deepseek/deepseek-v4-pro. Run it in the same shell.The Python and Node.js examples use the OpenAI SDK. Install it with pip install openai or npm install openai. Save the Node.js example in a file ending in .mjs, because it uses import and top-level await.
4

Check the reply

The call works when choices[0].message.content holds a greeting. Python and Node.js print only that field. cURL prints the whole JSON response.
5

Check usage

Token usage for Model API requests appears on Usage under MODEL APIS in the console.

Next steps

Browse models and pricing on the PPIO website.
Last modified on November 19, 2026