# Google Gemini API Configuration # ============================================================================ # OPTION 1: Google AI Studio (Default - Recommended for most users) # ============================================================================ # Get your API key: https://aistudio.google.com/apikey GEMINI_API_KEY=your_api_key_here # ============================================================================ # API Key Rotation (Optional - For high-volume usage) # ============================================================================ # Add multiple API keys for automatic rotation on rate limit errors. # Free tier accounts are heavily rate-limited; rotation helps distribute load. # # Format: GEMINI_API_KEY_N where N is 2, 3, 4, etc. # The primary GEMINI_API_KEY is always used first. # # GEMINI_API_KEY_2=your_second_api_key # GEMINI_API_KEY_3=your_third_api_key # GEMINI_API_KEY_4=your_fourth_api_key # # Features: # - Auto-rotates on RESOURCE_EXHAUSTED / 429 errors # - 60-second cooldown per key after rate limit # - Logs rotation events with --verbose flag # - Backward compatible: single key still works # ============================================================================ # OPTION 2: Vertex AI (Google Cloud Platform) # ============================================================================ # Uncomment these lines to use Vertex AI instead of Google AI Studio # GEMINI_USE_VERTEX=true # VERTEX_PROJECT_ID=your-gcp-project-id # VERTEX_LOCATION=us-central1 # ============================================================================ # Model Selection (Optional) # ============================================================================ # Override default models for specific capabilities # If not set, intelligent defaults are used based on task type # --- Image Generation --- # Used by: --task generate (image) # Default: gemini-2.5-flash-image (Nano Banana Flash - fast, cost-effective) # Alternative: imagen-4.0-generate-001 (production quality) # NOTE: All image generation requires billing - no free tier available (limit: 0) # Options: # gemini-2.5-flash-image - Nano Banana Flash: fast, ~$1/1M tokens (DEFAULT) # gemini-3-pro-image-preview - Nano Banana Pro: 4K text, reasoning (requires billing) # imagen-4.0-generate-001 - Imagen 4 Standard: production quality (~$0.02/image) # imagen-4.0-ultra-generate-001 - Imagen 4 Ultra: maximum quality (~$0.04/image) # imagen-4.0-fast-generate-001 - Imagen 4 Fast: speed-optimized (~$0.01/image) # IMAGE_GEN_MODEL=gemini-2.5-flash-image # --- Video Generation --- # Used by: --task generate-video (new capability) # Default: veo-3.1-generate-preview # NOTE: Video generation requires billing - no free tier fallback available # Options: # veo-3.1-generate-preview - Latest, native audio, frame control (requires billing) # veo-3.1-fast-generate-preview - Speed-optimized for business (requires billing) # veo-3.0-generate-001 - Stable, native audio, 8s videos (requires billing) # veo-3.0-fast-generate-001 - Stable fast variant (requires billing) # VIDEO_GEN_MODEL=veo-3.1-generate-preview # --- Multimodal Analysis --- # Used by: --task analyze, transcribe, extract # Default: gemini-2.5-flash # Options: # gemini-3-pro-preview - Latest, agentic workflows, 1M context # gemini-2.5-flash - Best price/performance (recommended) # gemini-2.5-pro - Highest quality # MULTIMODAL_MODEL=gemini-2.5-flash # --- Legacy Compatibility --- # Generic model override (use specific variables above instead) # GEMINI_MODEL=gemini-2.5-flash # GEMINI_IMAGE_GEN_MODEL=gemini-2.5-flash-image # ============================================================================ # MiniMax API Configuration (Optional - for image/video/speech/music generation) # ============================================================================ # Get your API key: https://platform.minimax.io/user-center/basic-information/interface-key # MINIMAX_API_KEY=your_minimax_api_key_here # --- MiniMax Image Generation --- # Models: image-01 (standard), image-01-live (enhanced) # Cost: ~$0.03/image | Rate: 10 RPM # MINIMAX_IMAGE_MODEL=image-01 # --- MiniMax Video Generation (Hailuo) --- # Models: MiniMax-Hailuo-2.3, MiniMax-Hailuo-2.3-Fast, MiniMax-Hailuo-02, S2V-01 # Cost: $0.25-0.52/video | Rate: 5 RPM # MINIMAX_VIDEO_MODEL=MiniMax-Hailuo-2.3 # --- MiniMax Speech/TTS --- # Models: speech-2.8-hd (best), speech-2.8-turbo (fast) # Cost: $30-50/1M chars | Rate: 60 RPM | 300+ voices, 40+ languages # MINIMAX_SPEECH_MODEL=speech-2.8-hd # --- MiniMax Music Generation --- # Models: music-2.5 (4-minute songs with vocals) # Cost: $0.03-0.075/gen | Rate: 120 RPM # MINIMAX_MUSIC_MODEL=music-2.5 # ============================================================================ # Rate Limiting Configuration (Optional) # ============================================================================ # Requests per minute limit (adjust based on your tier) # GEMINI_RPM_LIMIT=15 # Tokens per minute limit # GEMINI_TPM_LIMIT=4000000 # Requests per day limit # GEMINI_RPD_LIMIT=1500 # ============================================================================ # Video Generation Options (Optional) # ============================================================================ # Video duration in seconds (8s only for now) # VEO_DURATION=8 # Video resolution: 720p or 1080p # VEO_RESOLUTION=1080p # Aspect ratio: 16:9, 9:16, 1:1 (16:9 is default) # VEO_ASPECT_RATIO=16:9 # Frame rate: 24fps (fixed for now) # VEO_FPS=24 # Enable native audio generation # VEO_AUDIO=true # ============================================================================ # Image Generation Options (Optional) # ============================================================================ # Number of images to generate (1-4) # IMAGEN_NUM_IMAGES=1 # Image size: 1K or 2K (Ultra/Standard only) # IMAGEN_SIZE=1K # Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4 # IMAGEN_ASPECT_RATIO=1:1 # Enable person generation (restricted in EEA, CH, UK) # IMAGEN_PERSON_GENERATION=true # Add SynthID watermark (always enabled by default) # IMAGEN_WATERMARK=true # ============================================================================ # Processing Options (Optional) # ============================================================================ # Video resolution mode: default or low-res # low-res uses ~100 tokens/second vs ~300 for default # GEMINI_VIDEO_RESOLUTION=default # Audio quality: default (16 Kbps mono, auto-downsampled) # GEMINI_AUDIO_QUALITY=default # PDF processing mode: inline (<20MB) or file-api (>20MB, automatic) # GEMINI_PDF_MODE=auto # ============================================================================ # Retry Configuration (Optional) # ============================================================================ # Maximum retry attempts for failed requests # GEMINI_MAX_RETRIES=3 # Initial retry delay in seconds (uses exponential backoff) # GEMINI_RETRY_DELAY=1 # ============================================================================ # Output Configuration (Optional) # ============================================================================ # Default output directory for generated images # OUTPUT_DIR=./output # Image output format (png or jpeg) # IMAGE_FORMAT=png # Image quality for JPEG (1-100) # IMAGE_QUALITY=95 # ============================================================================ # Context Caching (Optional) # ============================================================================ # Enable context caching for repeated queries on same file # GEMINI_ENABLE_CACHING=true # Cache TTL in seconds (default: 1800 = 30 minutes) # GEMINI_CACHE_TTL=1800 # ============================================================================ # Logging (Optional) # ============================================================================ # Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL # LOG_LEVEL=INFO # Log file path # LOG_FILE=./logs/gemini.log # ============================================================================ # Pricing Reference (as of 2025-11) # ============================================================================ # Gemini 2.5 Flash: $1.00/1M input, $0.10/1M output # Gemini 2.5 Pro: $3.00/1M input, $12.00/1M output # Gemini 3 Pro: $2.00/1M input (<200k), $4.00 (>200k), $12/$18 output # Imagen 4: ~$0.01-$0.04 per image (varies by variant) # Veo 3: TBD (preview pricing) # Monitor: https://ai.google.dev/pricing # ============================================================================ # Notes # ============================================================================ # 1. Never commit API keys to version control # 2. Add .env to .gitignore # 3. API keys can be restricted in Google Cloud Console # 4. Monitor usage at: https://aistudio.google.com/apikey # 5. Free tier limits: 15 RPM, 1M-4M TPM, 1,500 RPD # 6. Vertex AI requires GCP authentication via gcloud CLI # 7. Model defaults (Dec 2025): # - Image gen: gemini-2.5-flash-image (Nano Banana Flash - default) # - Image gen: imagen-4.0-generate-001 (alternative for production) # - Video gen: veo-3.1-generate-preview # - Analysis: gemini-2.5-flash # 8. Preview models (veo-3.1, gemini-3) may have API changes