Skip to main content
Meta Llama models are available through Vertex AI using the :chatCompletions endpoint with OpenAI-compatible request and response format.

​
Provider constant

Use the Vertex::Meta constant to access Meta Llama models: 
use Prism\Vertex\Enums\Vertex;

Vertex::Meta  // 'vertex-meta'

​
Configuration

Llama 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
],
Express mode is not supported for Meta models. You must provide a project ID and location.

​
API schema

Meta models use the OpenAI schema, which provides:
  • :chatCompletions endpoint with OpenAI-compatible format
  • Publisher: meta
  • Model is prefixed in request body as meta/{model}
  • Supports text generation and structured output
  • No native embeddings support

​
Example models

  • llama-4-scout-17b-16e-instruct-maas
  • llama-3.3-70b-instruct-maas
  • llama-3.2-90b-vision-instruct-maas
  • llama-3.1-405b-instruct-maas
Meta model names on Vertex AI use the -maas suffix, indicating they’re part of the Model-as-a-Service (MaaS) offering.

​
Usage examples

​
Text generation

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

$response = Prism::text()
    ->using(Vertex::Meta, 'llama-4-scout-17b-16e-instruct-maas')
    ->withPrompt('Explain quantum computing in simple terms')
    ->asText();

echo $response->text;

​
Structured output

Llama models support structured output via response_format: { type: "json_object" } combined with a schema instruction: 
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'),
                ]
            )
        )
    ]
);

$response = Prism::structured()
    ->using(Vertex::Meta, 'llama-3.3-70b-instruct-maas')
    ->withSchema($schema)
    ->withPrompt('List the top 3 programming languages')
    ->asStructured();

$data = $response->structured;

​
Custom JSON instruction

You can customize the JSON schema instruction message: 
$response = Prism::structured()
    ->using(Vertex::Meta, 'llama-4-scout-17b-16e-instruct-maas')
    ->withSchema($schema)
    ->withProviderOptions([
        'jsonModeMessage' => 'Return JSON matching this schema: {schema}',
    ])
    ->withPrompt('List the top 3 programming languages')
    ->asStructured();

​
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::Meta, 'llama-3.3-70b-instruct-maas')
    ->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

Structured output via JSON mode with schema instruction

​
Endpoint details

Meta models use the :chatCompletions endpoint action, where the model field in the request body is prefixed with the publisher: 
{
  "model": "meta/llama-4-scout-17b-16e-instruct-maas",
  "messages": [...]
}
Prism Vertex handles this prefixing automatically—you only need to provide the model name.

​
Next steps

Structured output

Learn more about structured output

Other providers

Explore other MaaS providers

Build docs developers (and LLMs) love

Get started for freeTalk to us