Features
Unified async API for image, video, music, chat, and 3D generation
Two-endpoint workflow: POST to submit task, poll or webhook for result
Failed tasks are not charged — zero-charge for errors
Credit-based pricing, no subscriptions, credits never expire
Free playground to test models before integration
Image generation: text-to-image, image edit with Nano Banana, GPT Image, Seedream, FLUX, etc.
Video generation: text-to-video, image-to-video with Seedance, Kling, Sora 2, Veo 3.1, Wan
Music generation: Suno v4/v4.5/v5, ElevenLabs Music, vocal remover, cover, extend
Chat completions: Claude Sonnet 5 (1M context, 128K output), Gemini 3, GPT-5, DeepSeek
3D generation: Meshy 6, Hunyuan 3D v3.1, Tripo3D H3.1
Audio tools: ElevenLabs TTS, Gemini TTS, xAI TTS
Avatar generation: Kling Avatar 2.0
Automatic aspect ratio support for video generation
Supports 4K video output with Seedance 2 and Omni Flash
Model providers include Google, OpenAI, Kling, Seedance, Alibaba, Anthropic, Black Forest Labs, xAI, MiniMax, DeepSeek,
Agent One autonomous AI agent for video creation
Long-term memory for consistent clips across projects
Edit multiple shots simultaneously (costumes, locations, characters)
AI-assisted scriptwriting and storyboarding
Full timeline editor with AI capabilities
Real-time multiplayer collaboration with live cursors
Access to 200+ AI models (video, image, audio, music)
AI voice generator and voice cloning
AI video translator and subtitles
Custom agent creation (cinematographer, sound designer, etc.)
Stock media integration (iStock, Storyblocks)
Face swap and other quick AI tools
AI image generation and enhancement
SOC 2 & ISO aligned, GDPR compliant
