Skip to main content
Google Gemini models use the native Vertex AI generateContent and predict endpoints, providing full support for text generation, structured output, and embeddings.

​
Provider constant

Use the Vertex::Gemini constant to access Google Gemini models: 
use Prism\Vertex\Enums\Vertex;

Vertex::Gemini  // 'vertex-gemini'

​
Configuration

Gemini models use the shared vertex configuration block: 
'vertex' => [
    'project_id'  => env('VERTEX_PROJECT_ID'),
    'location'    => env('VERTEX_LOCATION', 'us-central1'),
    'credentials' => env('VERTEX_CREDENTIALS'), // path to service-account.json
    // OR use api_key instead:
    // 'api_key' => env('VERTEX_API_KEY'),
],

​
Express mode support

Gemini is the only provider that supports Express mode, which allows you to use an API key without providing a project ID or location: 
'vertex' => [
    'api_key' => env('VERTEX_API_KEY'),
    // project_id and location omitted — triggers Express mode
],
Express mode only works with Google Gemini models. Partner models require Standard mode with project ID and location.

​
API schema

Gemini models use the Gemini schema, which provides:
  • Native generateContent endpoint for text generation
  • Native predict endpoint for embeddings
  • Native structured output via response_mime_type: application/json and response_schema
  • Publisher: google

​
Example models

  • gemini-2.5-flash
  • gemini-2.5-pro
  • gemini-2.0-flash-exp
  • gemini-1.5-pro
  • gemini-1.5-flash

​
Usage examples

​
Text generation

use Prism\Prism\Prism;
use Prism\Vertex\Enums\Vertex;

$response = Prism::text()
    ->using(Vertex::Gemini, 'gemini-2.5-flash')
    ->withPrompt('Explain quantum computing in simple terms')
    ->asText();

echo $response->text;

​
Structured output

Gemini has native structured output support, which constrains the model to produce valid JSON matching your schema: 
use Prism\Prism\Prism;
use Prism\Vertex\Enums\Vertex;
use Prism\Prism\Schema\ObjectSchema;
use Prism\Prism\Schema\StringSchema;
use Prism\Prism\Schema\ArraySchema;

$schema = new ObjectSchema(
    name: 'languages',
    description: 'Top programming languages',
    properties: [
        new ArraySchema(
            'languages',
            'List of programming languages',
            items: new ObjectSchema(
                name: 'language',
                description: 'Programming language details',
                properties: [
                    new StringSchema('name', 'The language name'),
                    new StringSchema('popularity', 'Popularity description'),
                ]
            )
        )
    ]
);

$response = Prism::structured()
    ->using(Vertex::Gemini, 'gemini-2.5-flash')
    ->withSchema($schema)
    ->withPrompt('List the top 3 programming languages')
    ->asStructured();

$data = $response->structured;
Under the hood, Gemini structured output uses:
  • response_mime_type: application/json
  • response_schema with your JSON schema
  • The model is constrained to only produce valid JSON matching the schema

​
Embeddings

Gemini is the only provider in Prism Vertex that supports embeddings: 
use Prism\Prism\Prism;
use Prism\Vertex\Enums\Vertex;

$response = Prism::embeddings()
    ->using(Vertex::Gemini, 'text-embedding-005')
    ->fromInput('The sky is blue')
    ->asEmbeddings();

$embeddings = $response->embeddings;

​
Multi-turn conversation

use Prism\Prism\Prism;
use Prism\Vertex\Enums\Vertex;
use Prism\Prism\ValueObjects\Messages\UserMessage;
use Prism\Prism\ValueObjects\Messages\AssistantMessage;

$response = Prism::text()
    ->using(Vertex::Gemini, 'gemini-2.5-flash')
    ->withMessages([
        new UserMessage('What is the capital of France?'),
        new AssistantMessage('The capital of France is Paris.'),
        new UserMessage('What is its population?'),
    ])
    ->asText();

echo $response->text;

​
Capabilities

Text generation

Full support for text generation with multi-turn conversations

Structured output

Native structured output with schema constraints

Embeddings

Generate embeddings for text

​
Next steps

Structured output

Learn more about structured output

Configuration

See all configuration options

Build docs developers (and LLMs) love

Get started for freeTalk to us