Unified API for image and video generation with transparent, credit-based pricing
Generate cinematic AI video with Gemini Omni — native audio, chat-based editing, multi-reference control
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Freemium
Pricing
1 credit = $0.01. Billed per image or per second for video. Gemini 3.1 Flash Lite Image: 2 credits/image. GPT Image 2.5 Flare: from 1 credit/image (1024x1024 low). GPT Image 2: from 1 credit/image. FLUX.2 Pro: from 3 credits/image. Seedream 5.0 Pro: from 4 credits/image. Qwen Image 3.0: 3 credits/im
Basic: $13.99/month (save 40% yearly) with 440 credits/month. Pro: $39.99/month (save 40% yearly) with 1,760 credits/month. Enterprise: $69.99/month (save 40% yearly) with 3,520 credits/month. Credits packs available for purchase.
Key features
Unified authentication across multiple AI providers
Transparent credit pricing visible before each request
Switch between models with single request field change
Async video generation with task tracking
Automatic refunds for eligible failed requests
Usage monitoring and credit tracking in developer console
Support for 10+ image and video models
API documentation optimized for AI coding tools
Native audio generation synchronized with video in a single pass
Chat-based editing with frame-by-frame control
Multi-reference input control for images, video clips, and audio tracks
Up to 2K resolution with clips up to 15 to 20 seconds
Access to multiple AI models including Kling, Veo, and Seedream
Commercial usage rights and watermark-free output
Browser-based with no software installation
AI Voice Generator
High resolution output
Priority generation queue
What makes it different
One account and API key for all supported models instead of separate accounts per provider
Transparent credit costs before making requests with no token guessing
Lower prices than official APIs through volume rates
Automatic refund protection for eligible failed tasks
Consistent API format across different model providers
Unified video and audio generation without separate post-production merging
Long-context window preserving character consistency across edits
Chat-based editing using plain language instead of timeline tools
Multi-reference input supporting text, images, video clips, and audio simultaneously
Global browser access without geographic restrictions