All provider guides

Set up Z.AI

PHP

Researched from Z.AI's official documentation on 2026-11-02. Not yet walked through end to end.

  1. Current: Sign in to the Open Platform

    Register or sign in to Z.AI using the platform link in the official quickstart.

  2. Not started: Create a standard API key

    Open API Keys management and create a Standard API Key for this application. Store it privately on your machine.

  3. Not started: Check balance and endpoint

    Review billing and choose a model available to your standard API account. Keep the model, key and endpoint compatible; Coding Plan configuration is a separate workflow.

  4. Not started: Configure your .env

    Use the environment names below in your own application. Keep its environment file out of source control. Never paste a key into this website.

  5. Not started: Run the local check

    Choose a model you can use and run the matching example below on your own machine. Check any applicable usage charges first.

This provider is available in PHP Prism. The TypeScript and Python ports do not implement it.

Configure and verify locally

Environment names and defaults below come from the installed package. Choose a model you can use by setting PRISM_SETUP_MODEL on your machine. Run the verification only when you are ready for one billed request. No request is sent by this page.

Approximate text cost is input tokens × your model’s input rate, plus at most 32 output tokens × its output rate, divided by the rate’s token unit. Add any provider fees. Check your model and region’s current price; the token limit is not a money cap.

php environment names
# url (default)
# Z_URL=https://api.z.ai/api/paas/v4
# Set Z_API_KEY privately if required for your configuration.
php local verification
use Prism\Prism\Facades\Prism;

// Run in your own configured Laravel app (for example, php artisan tinker).
$model = getenv('PRISM_SETUP_MODEL');
if (!$model) {
    throw new RuntimeException('Set PRISM_SETUP_MODEL to your model.');
}
try {
    $result = Prism::text()
        ->using('z', $model)
        ->withPrompt('Say hello.')
        ->withMaxTokens(32)
        ->asText();
    echo $result->text, PHP_EOL;
} catch (Throwable $error) {
    echo get_class($error), PHP_EOL;
}

Official sources