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,
Ray 3.2: frame-by-frame video control and continuity across cuts
Uni-1.1: brand intelligence with style and character references
Luma Skills: reusable creative workflows for consistent output
Modify Video: video-to-video editing
Reframe: outpaint images and reframe videos
Camera Motion Concepts: learnable camera controls
Automatic continuity across video cuts
Cinematic quality finishing
Agent-driven research and refinement across video, image, audio, text
Team members and admins management
Fast variant generation: ten directions before standup
API access for Ray 3.2 and Uni-1.1
Third-party model integration (Veo 3.1, Kling Omni, GPT Image 2)
Image generation with GPT Image 2, Nano Banana, Seedream
Audio generation: ElevenLabs TTS, SFX, music
