Models
Every model runs behind the same task-based API. Filter by modality or search by name, vendor, or capability.
AI Music 2.5
ElevenLabs
Generate original music from text descriptions
Audio to MP3
Muke Labs
Convert common audio uploads into a standalone MP3 file
Auto Video Watermark Remover
Alibaba
Remove logos, captions, and watermarks from a video without drawing a mask
Character Concept Board
Muke Labs
Character model sheets for video and story production
Claude Fable 5.1
Anthropic
Claude Fable 5.1
Claude Opus 4.5
Anthropic
Older Claude Opus generation kept for compatibility
Claude Opus 4.6
Anthropic
Previous Claude Opus generation for agentic coding and analysis
Claude Opus 4.7
Anthropic
Latest Claude Opus model for long-running agentic work
Claude Opus 5.5
Anthropic
Claude Opus 5.5
Claude Sonnet 4.6
Anthropic
Nuanced writing and detailed analysis at Sonnet pricing
Claude Sonnet 5.5
Anthropic
Claude Sonnet 5.5
DeepSeek V3.1 Terminus
DeepSeek
Older DeepSeek V3.1 route kept for generation comparison
DeepSeek V3.2
DeepSeek
Previous DeepSeek generation for economical chat and coding
DeepSeek V4 Flash
DeepSeek
Frontier-class reasoning for high-frequency tasks
DeepSeek V4 Pro
DeepSeek
Latest DeepSeek Pro model for advanced reasoning and coding
DeepSeek V4.1 Flash
DeepSeek
DeepSeek V4.1 Flash
Digital Human - HeyGen
HeyGen
Generate or lip-sync avatar videos from media plus uploaded speech audio
Digital Human - InfiniTalk
InfiniTalk
Create talking-avatar videos from a portrait image plus voice audio
Flux 2 Dev
Black Forest Labs
Fast creative drafts and prompt testing
Flux 2 Flex
Black Forest Labs
Balanced Flux 2 quality with a flexible image workflow
Flux 2 Pro
Black Forest Labs
Photorealistic quality with precise prompt following
FLUX Inpainting
Black Forest Labs
AI-powered image inpainting with text-guided generation
Gemini 3 Flash Preview
Previous Gemini Flash preview retained for stable workflows
Gemini 3.1 Flash Lite
Low-latency Gemini 3.1 model for high-volume everyday tasks
Gemini 3.1 Pro Preview
Latest Gemini Pro reasoning model for multimodal agent work
Google Omni Flash
Create, reference, and edit multimodal video with native audio
GPT Image 2
OpenAI
Image model for precise text, layouts, and native edits
GPT Image 2.5
OpenAI
High-detail image generation and precision editing
GPT-5.4
OpenAI
Previous OpenAI frontier model with 1M context
GPT-5.5
OpenAI
Latest OpenAI frontier model for complex reasoning and coding
GPT-6 Astra
OpenAI
GPT-6 Astra
GPT-6 Luna
OpenAI
GPT-6 Luna
GPT-6.1 Sol
OpenAI
GPT-6.1 Sol
GPT-Image-1.5
OpenAI
Versatile editing with natural language instructions
Graphics Image Upscale
Muke Labs
Upscale posters and text-heavy graphics while preserving layout
Grok Imagine 2.0
xAI
Fast creative generation with a distinctive visual style
Grok Video
xAI
Realistic video with fast turnaround
Grok Video v1.5
xAI
Latest Grok image-to-video with native audio
Hailuo 2.3
MiniMax
Cinematic quality with fast generation speed
Happy Horse
Alibaba
#1 ranked — native audio & 7-language lip-sync
High Fidelity Image Upscale
Muke Labs
Fine-detail enhancement for demanding source images
Kling
Kling
Video creation, effects, motion transfer and lip sync
Kling 2.5
Kling
Fast video drafts with quick turnaround
Kling O1
Kling
Kling O1 — first/last-frame, omni-reference, video reference and video edit
Kling O3
Kling
Kling O3 — image-to-video, omni-reference, video reference and video edit
LaMa Inpainting
Muke Labs
Remove watermarks, objects, or imperfections from images
LTX Video 2.5
Lightricks
Fast video generation for rapid iteration
Magnific Upscaler
Magnific AI
AI-powered image upscaling with creative enhancement
Midjourney
Midjourney
Latest Midjourney v8.2 image generation with follow-up actions
MiniMax H3
MiniMax
Create high-detail videos from text, or from image, video, and audio references
Nano Banana 2
Ultra-realistic image creation with multi-reference support
Nano Banana 2 Lite
Fast 1K image creation and editing
Nano Banana Pro
Premium image model with stronger reasoning and text rendering
Outfit & Accessory Changer
Muke Labs
Change clothing and accessories while keeping the person recognizable
Photo Angle Changer
Muke Labs
Change the camera angle while preserving the source subject
Photo Background Changer
Muke Labs
Replace the background with cleaner commercial scenes
Photo Element Replacer
Muke Labs
Replace an object or person with an uploaded reference and optional region hint
Photo Face Swap
Muke Labs
Swap a face into a target photo while preserving the scene
Photo Lighting Changer
Muke Labs
Change lighting, shadows, and mood without changing the subject
Qwen 3.7 Flash
Alibaba
Fast multimodal Qwen Flash for prompt rewriting and everyday chat
Qwen 3.8 Flash
Alibaba Qwen
Qwen 3.8 Flash
Restore Image
Muke Labs
Reconstruct clarity in damaged or low-quality images
Seedance 2.0 Fast
ByteDance
Faster video mode for previewing movement and multi-reference ideas
Seedance 2.0 Standard
ByteDance
Higher-quality video mode for movement and multi-reference work
Seedance 2.5
ByteDance
Native 30-second clips with multi-reference control
Seedream 5.0 Lite
ByteDance
Artistic style with excellent Chinese text rendering
Seedream 5.0 Pro
ByteDance
High-fidelity final images with precise composition and subject consistency
Sound FX
ElevenLabs
Create any sound effect from a text description
Standard Image Upscale
Muke Labs
Balanced enlargement for everyday images
Suno Music
Suno
Generate full songs from descriptions or lyrics
TTS Flash
ElevenLabs
Natural text-to-speech with 30+ languages
Veo 3.1
Native audio and ultra-realistic motion
Video Audio Splitter
Muke Labs
Extract a silent video and standalone MP3 from one upload
Video HD Upscaler
Topaz Labs
Upscale videos to 720p, 1080p, 4K or higher with AI
Video Prompt Storyboard Reverse Engineer
Muke Labs
Turn a reference video into reusable prompts and a visual storyboard control board
Video Storyboard Control Board
Muke Labs
GPT Image 2.5 pre-production board for controllable AI video
Video Watermark Remover
Alibaba
Remove moving video watermarks with regional repainting
Voice Clone
ElevenLabs
Clone any voice from a short audio sample
Wan 2.7
Alibaba
Artistic video with rich creative expression
Wan 3.0
Alibaba
Generate native-audio video from text, frames, or mixed media references
Wan VACE
Alibaba
Mask-guided video inpainting and regional editing