Gemini

Direct access to Google's Gemini models. Use it when you need broad single-vendor coverage — chat text with streaming, image generation, speech synthesis, transcription, file storage, and embeddings, including multimodal embeddings over images, audio, documents, and video.

Capabilities

Text with streaming, image and audio generation, transcription, text and multimodal embeddings, plus file storage and file-backed stores. Provider tools: code execution, file search, web fetch, and web search (details).

Configuration

Configure via environment variables. config/ai.php only forwards them with env() — set the values in .env or the host environment, never hardcode keys in the config file.

// In config/ai.php
return [
    'Ai' => [
        'providers' => [
            'gemini' => [
                'className' => 'Crustum\Ai\Providers\GeminiProvider',
                'key' => env('GEMINI_API_KEY'),
                'url' => env('GEMINI_URL', 'https://generativelanguage.googleapis.com/v1beta'),
                'models' => [
                    'text' => [
                        'default' => env('GEMINI_TEXT_MODEL', 'gemini-3.8-flash'),
                        'cheapest' => env('GEMINI_TEXT_MODEL_CHEAPEST', 'gemini-3.1-flash-lite'),
                        'smartest' => env('GEMINI_TEXT_MODEL_SMARTEST', 'gemini-3.8-flash'),
                    ],
                    'image' => [
                        'default' => env('GEMINI_IMAGE_MODEL', 'gemini-3.1-flash-image'),
                    ],
                    'audio' => [
                        'default' => env('GEMINI_AUDIO_MODEL', 'gemini-3.8-flash-lite-tts'),
                    ],
                    'transcription' => [
                        'default' => env('GEMINI_TRANSCRIPTION_MODEL', 'gemini-3.5-transcribe'),
                    ],
                    'embeddings' => [
                        'default' => env('GEMINI_EMBEDDINGS_MODEL', 'gemini-embedding-2'),
                        'dimensions' => (int)env('GEMINI_EMBEDDINGS_DIMENSIONS', 3072),
                    ],
                ],
            ],
        ],
    ],
];

Config key	Env var	Purpose
className	—	Provider class. Keep the default unless subclassing.
key (apiKey also accepted)	GEMINI_API_KEY	Key from Google AI Studio / Cloud console. Required.
url	GEMINI_URL	API base URL. Change only for proxies or gateways.
models.text.default	GEMINI_TEXT_MODEL	Chat model for normal calls.
models.text.cheapest	GEMINI_TEXT_MODEL_CHEAPEST	Budget model for cost-sensitive calls.
models.text.smartest	GEMINI_TEXT_MODEL_SMARTEST	Flagship model for the hardest tasks.
models.image.default	GEMINI_IMAGE_MODEL	Image generation model.
models.audio.default	GEMINI_AUDIO_MODEL	Text-to-speech model.
models.transcription.default	GEMINI_TRANSCRIPTION_MODEL	Speech-to-text model.
models.embeddings.default	GEMINI_EMBEDDINGS_MODEL	Embeddings model.
models.embeddings.dimensions	GEMINI_EMBEDDINGS_DIMENSIONS	Vector width. Must match the embeddings model.
headers	— (config only)	Extra HTTP headers merged into every request. Add as a plain array if needed.

Model selection priority per call: explicit model: argument wins, then the matching models.* value above, then the provider's built-in fallback.

See also

• Providers — capability matrix
• Images — generation and storage
• Audio — speech and transcription
• Embeddings — vectors and caching