OpenAIProvider

Use OpenAI directly, or route through any OpenAI-compatible endpoint (OpenRouter, Ollama, Cloudflare AI Gateway, llama.cpp) by setting baseUrl. OpenAIProvider is also the parent class for GeminiProvider and MistralProvider.

Construction

public function __construct(
    ProviderConfig $config,
    ClientContract|null $client = null,
    Closure|null $sleep = null,
)

Methods

generateObject

Builds a chat.completions request with response_format: { type: 'json_schema', strict: true }, sends it, and returns the decoded JSON object.

$provider->generateObject(
    messages: [
        ['role' => 'system', 'content' => 'Return JSON only.'],
        ['role' => 'user', 'content' => 'Pick three colors.'],
    ],
    schema: [
        'type' => 'object',
        'properties' => ['colors' => ['type' => 'array', 'items' => ['type' => 'string']]],
        'required' => ['colors'],
        'additionalProperties' => false,
    ],
);

Throws ProviderException when the decoded response is not a JSON object, or when the upstream call returns 4xx/5xx after the retry chain.

generateText

Sends a chat.completions request without response_format and returns the message content.

$provider->generateText(
    messages: [
        ['role' => 'user', 'content' => 'Describe three primary colors.'],
    ],
);

Throws ProviderException when the response carries no text content, or when the upstream call returns 4xx/5xx after the retry chain.

Retry Behavior

Up to 3 attempts on RateLimitException (429), ServerException (5xx), TransporterException (network), and ErrorException with status 429 or ≥500. The wrapper honors Retry-After, falling back to 2^attempt seconds.

After 3 failed attempts the wrapper throws ProviderException with reason: 'request failed: <message>', responseExcerpt (body shortened to 200 chars), httpCode, and previous set to the original Throwable.

OpenAI-Compatible Endpoints

OpenAIProvider doubles as the transport for any OpenAI-compatible API. Configure the base URL and model in config.php:

'providers' => [
    'openai' => [
        'apiKey' => env('OPENROUTER_API_KEY'),
        'baseUrl' => 'https://openrouter.ai/api/v1',
        'model' => 'anthropic/claude-3.5-sonnet',
    ],
],

'providers' => [
    'openai' => [
        'apiKey' => 'sk-no-key-required',
        'baseUrl' => 'https://llama.example.com/v1',
        'model' => 'llama-3.2-3b-instruct',
    ],
],

'providers' => [
    'openai' => [
        'apiKey' => env('OPENAI_API_KEY'),
        'baseUrl' => 'https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/openai',
        'model' => 'gpt-5.4',
    ],
],

For Chat Completions vs. Responses API selection, see the api option.

Provider-Specific Options

Anything in providers.openai that isn't apiKey, model, or baseUrl lands in ProviderConfig::$options and is spread into every request payload:

'providers' => [
    'openai' => [
        'apiKey' => env('OPENAI_API_KEY'),
        'temperature' => 0.7,
        'reasoning_effort' => 'medium',
        'top_p' => 0.9,
    ],
],

The plugin doesn't validate option names – anything that doesn't match an OpenAI Chat Completions field is sent as-is and may be rejected upstream.