Abracadabrax · Model catalog
86 AI models in one place
Abracadabrax runs 86 image, editing, video, upscaling and music models from one prompt bar and one credit balance. This page lists every model with what it costs per run; the family pages explain each version and how to prompt it.
Model families
Nano BananaNano Banana image generation online: run Nano Banana 2, Pro and Lite from Google side by side, with text rendering and multi-image references.KlingKling AI video generator online: make cinematic clips with native audio using Kling 3.0 Pro, Standard, O3 Pro and 2.6 Pro, plus Kling virtual try-on.SeedanceSeedance 2.0 and Seedance 2.5 online: ByteDance video models with audio and lip-sync, plus Reference versions that keep your people and products.Grok ImagineGrok Imagine online: generate images with Grok Imagine and Image 2.0, edit photos, and make clips with sound on Grok Imagine Video 1.5 from xAI.GPT ImageChatGPT image generator models online: GPT Image 2, GPT Image 2.5 Flare and Sunburst, and GPT Image 1.5 from OpenAI, with an Edit version of each.VeoVeo 3 video generation online: run Google Veo 3.1 for cinematic clips with audio from a text prompt, or Veo 3.1 Fast for quicker renders.PixVersePixVerse V6 online: make stylized, social-ready video clips from a text prompt, next to other AI video models on one Abracadabrax credit balance.IdeogramIdeogram online: make posters, logos and typography that read right with Ideogram 4 and Ideogram v3, next to other image models on one balance.KreaKrea AI image generation online: Krea 2 Large makes aesthetic, art-directed images with natural textures, next to other models on one balance.FluxFlux AI image generator online: Flux 2 Max, Pro, Flex and Flux 2, Flux Pro Ultra, Pro and Dev, plus Flux Kontext and Flux 2 editing, from BFL.WanWan AI video online: run Alibaba's Wan 3.0 for 1080p clips with native audio and Wan 2.7 for 1080p text-to-video, next to other video models.TopazTopaz video AI upscaling online: sharpen and enlarge videos and images up to 4x with Topaz Video Upscale and Topaz Image Upscale, from one balance.Z-ImageZ Image Turbo online: Tongyi-MAI's ultra fast image model for photoreal drafts, run next to other image models on one Abracadabrax credit balance.SeedreamSeedream online: ByteDance image models Seedream 5.0 Pro, 5 Lite and 4.5, with multi-image editing versions that take several reference images.Qwen ImageQwen Image Edit online: Alibaba's Qwen Image 3 for text in any language, Qwen Image 3 Edit for text-aware changes, and open-weights Qwen Image.
Image generation models
| Model | Maker | Credits | Speed | What it does |
|---|---|---|---|---|
| Nano Banana 2 | 60 | Fast | Gemini 3.1 Flash — reasoning, text rendering, character consistency. | |
| Nano Banana Pro | 113 | Medium | Gemini 3 Pro — reasoning, 4K, up to 14 reference images. | |
| Nano Banana | 30 | Fast | Gemini 2.5 Flash — text+images to image, fast. | |
| GPT Image 2 | OpenAI | 158 | Medium | OpenAI — text rendering + photorealism, up to 4K. |
| GPT Image 1.5 | OpenAI | 100 | Medium | High fidelity, GPT-5 architecture. |
| Flux Pro | Black Forest Labs | 41 | Fast | BFL — max quality, 12B params. |
| Flux Pro Ultra | Black Forest Labs | 45 | Medium | BFL — ultra HD, up to 4K. |
| Flux Dev | Black Forest Labs | 19 | Fast | BFL — open-weights, flexible. |
| Flux 2 | Black Forest Labs | 23 | Fast | BFL — second generation Flux. |
| Flux 2 Pro | Black Forest Labs | 41 | Medium | BFL — Flux 2 Pro, top quality. |
| Seedream 4.5 | ByteDance | 30 | Fast | ByteDance — gen+edit unified, up to 4K. |
| Seedream 5 Lite | ByteDance | 27 | Fast | ByteDance — Seedream 5 fast, up to 4K. |
| Grok Imagine | xAI | 38 | Fast | xAI — highly aesthetic generation, up to 2K. |
| GPT Image 2.5 Flare | OpenAI | 30 | Medium | OpenAI — GPT Image 2.5 Flare, sharp text and photoreal detail. |
| GPT Image 2.5 Sunburst | OpenAI | 30 | Medium | OpenAI — GPT Image 2.5 Sunburst, vivid color and lighting. |
| Grok Imagine Image 2.0 | xAI | 45 | Fast | xAI — second-generation Grok image model, wide aspect ratios. |
| Qwen Image 3 | Alibaba | 30 | Fast | Alibaba — Qwen Image 3, strong text rendering in any language. |
| Ideogram 4 | Ideogram | 12 | Fast | Ideogram — posters, logos and typography that read right. |
| Krea 2 Large | Krea | 45 | Medium | Krea — aesthetic, art-directed images with natural textures. |
| Flux 2 Max | Black Forest Labs | 53 | Medium | BFL — Flux 2 at maximum fidelity. |
| Flux 2 Flex | Black Forest Labs | 38 | Medium | BFL — Flux 2 Flex, tuned for typography and fine detail. |
| Seedream 5.0 Pro | ByteDance | 102 | Medium | ByteDance — Seedream 5.0 Pro, 2K images with rich detail. |
| Nano Banana 2 Lite | 38 | Fast | Google — lighter Nano Banana 2, fast 1K images. | |
| Nano Banana Lite | 38 | Fast | Google — lightweight Nano Banana for quick drafts. | |
| Ideogram v3 | Ideogram | 45 | Medium | Ideogram — v3, reliable text and graphic design layouts. |
| Qwen Image | Alibaba | 15 | Fast | Alibaba — open-weights Qwen Image, good with text. |
| Z-Image Turbo | Tongyi | 5 | Fast | Tongyi-MAI — ultra fast, ultra cheap photoreal drafts. |
Image editing models
| Model | Maker | Credits | Speed | What it does |
|---|---|---|---|---|
| GPT Image 2 Edit | OpenAI | 158 | Medium | OpenAI — photorealistic image-to-image with optional mask. |
| Flux Kontext | Black Forest Labs | 30 | Fast | BFL — edit with text + reference image. |
| Flux 2 Edit | Black Forest Labs | 30 | Fast | BFL — Flux 2 image-to-image editing. |
| Flux 2 Pro Edit | Black Forest Labs | 53 | Medium | BFL — Flux 2 Pro image editing, top quality. |
| Seedream 4.5 Edit | ByteDance | 30 | Fast | ByteDance — multi-image editing (max 10 refs). |
| Seedream 5 Lite Edit | ByteDance | 30 | Fast | ByteDance — multi-image editing Seedream 5 (max 10 refs). |
| Grok Imagine Edit | xAI | 38 | Fast | xAI — precise image editing. |
| GPT Image 2.5 Flare Edit | OpenAI | 64 | Medium | OpenAI — edit a photo with GPT Image 2.5 Flare. |
| GPT Image 2.5 Sunburst Edit | OpenAI | 64 | Medium | OpenAI — edit a photo with GPT Image 2.5 Sunburst. |
| Grok Imagine 2.0 Edit | xAI | 75 | Fast | xAI — Grok Imagine 2.0 multi-image editing. |
| Qwen Image 3 Edit | Alibaba | 57 | Fast | Alibaba — Qwen Image 3 editing, text-aware changes. |
| Flux 2 Max Edit | Black Forest Labs | 98 | Medium | BFL — Flux 2 Max editing at maximum fidelity. |
| Flux 2 Flex Edit | Black Forest Labs | 113 | Medium | BFL — Flux 2 Flex editing, precise text and detail. |
| Seedream 5.0 Pro Edit | ByteDance | 112 | Medium | ByteDance — Seedream 5.0 Pro multi-image editing. |
| Nano Banana Lite Edit | 38 | Fast | Google — quick, light Nano Banana edits. | |
| GPT Image 1.5 Edit | OpenAI | 168 | Medium | OpenAI — GPT Image 1.5 editing with high input fidelity. |
Video models
| Model | Maker | Credits | Lengths | What it does |
|---|---|---|---|---|
| Veo 3.1 | 1,200 for 4s | 4s, 6s, 8s | Cinematic quality + audio, up to 8s. | |
| Veo 3.1 Fast | 451 for 4s | 4s, 6s, 8s | Veo 3.1 fast generation, up to 8s. | |
| Kling 3.0 Pro | Kuaishou | 630 for 5s | 5s, 10s | Cinematic + native audio, multi-shot. |
| Kling 3.0 Standard | Kuaishou | 473 for 5s | 5s, 10s | Cinematic + native audio, budget tier. |
| Kling 2.6 Pro | Kuaishou | 525 for 5s | 5s, 10s | Native audio, high quality. |
| Kling O3 Pro | Kuaishou | 525 for 5s | 5s, 10s | Omni — multi-image, up to 10s. |
| Seedance 2.0 | ByteDance | 1,136 for 5s | 5s, 8s, 10s, 12s | Unified audio-video, lip-sync, cinematic quality. |
| Seedance 2.0 Fast | ByteDance | 908 for 5s | 5s, 8s, 10s, 12s | Fast generation, lower latency. |
| Seedance 1.5 Pro | ByteDance | 300 for 5s | 5s, 8s, 10s, 12s | Native audio, cinematic quality. |
| Seedance 1 Lite | ByteDance | 81 for 3s | 3s, 4s, 5s, 8s, 10s, 12s | Fast and lightweight. |
| Grok Imagine Video | xAI | 263 for 5s | 5s | Fast video generation with audio, up to 10s. |
| Topaz Video Upscale | Topaz Labs | 94 for 5s | 5s | Professional AI video upscaling up to 4x. |
| MiniMax H3 Max | MiniMax | 300 for 5s | 5s, 10s | MiniMax — H3 Max, expressive motion and physics. |
| MiniMax H3 Max Turbo | MiniMax | 150 for 5s | 5s, 10s | MiniMax — H3 Max at half the cost, faster renders. |
| Wan 3.0 | Alibaba | 750 for 5s | 5s, 10s | Alibaba — Wan 3.0, 1080p with native audio. |
| LTX 2.5 Pro | Lightricks | 765 for 6s | 6s, 8s, 10s | Lightricks — LTX 2.5 Pro, 1080p with native audio. |
| LTX 2.5 Fast | Lightricks | 585 for 6s | 6s, 8s, 10s | Lightricks — LTX 2.5 Fast, quick 1080p clips with audio. |
| Grok Imagine Video 1.5 | xAI | 525 for 5s | 5s, 10s | xAI — Grok Imagine Video 1.5, straight from a prompt. |
| PixVerse V6 | PixVerse | 169 for 5s | 5s, 10s | PixVerse — V6, stylized and social-ready clips. |
| Happy Horse 1.1 | Alibaba | 675 for 5s | 5s, 10s | Alibaba — Happy Horse 1.1, smooth 1080p motion. |
| Gemini Omni Flash | 469 for 5s | 5s, 8s, 10s | Google — Gemini Omni Flash, video with sound from one prompt. | |
| Seedance 2.5 | ByteDance | 1,774 for 5s | 5s, 8s, 10s, 12s | ByteDance — Seedance 2.5, audio-video in one pass, up to 12s. |
| Wan 2.7 | Alibaba | 563 for 5s | 5s, 10s | Alibaba — Wan 2.7, 1080p text-to-video. |
| Seedance 2.0 Reference | ByteDance | 1,134 for 5s | 5s, 8s, 10s, 12s | ByteDance — video that keeps the people and products in your reference images. |
| Seedance 2.5 Reference | ByteDance | 1,774 for 5s | 5s, 8s, 10s, 12s | ByteDance — Seedance 2.5 guided by your reference images. |
Upscalers
| Model | Maker | Credits | Speed | What it does |
|---|---|---|---|---|
| Topaz Image Upscale | Topaz Labs | 60 | Fast | Topaz — professional AI upscaling up to 4x. |
| Clarity Skin | ClarityAI | 38 | Medium | Upscaling + skin and texture enhancement. |
| ESRGAN 4x | ESRGAN | 5 | Fast | Classic AI upscaling up to 4x. |
| CCSR Upscaler | CCSR | 5 | Medium | Content-Consistent Super Resolution. |
| Crystal Upscaler | ClarityAI | 38 | Medium | Ultra-sharp crystal clarity upscaling. |
Virtual try-on
| Model | Maker | Credits | Speed | What it does |
|---|---|---|---|---|
| FASHN Try-On | FASHN | 57 | Fast | Virtual try-on (ref 1 = person, ref 2 = garment). |
| Kling Kolors Try-On | Kuaishou | 53 | Fast | Kling virtual try-on (ref 1 = person, ref 2 = garment). |
| CAT-VTON | CAT-VTON | 15 | Fast | Virtual try-on (ref 1 = person, ref 2 = garment). |
Music models
| Model | Maker | Credits | Lengths | What it does |
|---|---|---|---|---|
| Abracadabrax v2 | Abracadabrax | 113 | — | Full songs with vocals from a style prompt + lyrics. Premium quality. |
| Abracadabrax v1 | Abracadabrax | 60 for 30s | 30s, 60s, 120s, 180s | Songs with sung lyrics — fast and economical. |
| Abracadabrax Studio | Abracadabrax | 300 for 30s | 30s, 60s, 120s, 180s, 300s | Studio-grade music with fine control. Max quality. |
| Abracadabrax Instrumental | Abracadabrax | 30 | 30s, 60s, 120s, 180s, 300s | Instrumental & soundtrack, cleared for commercial use, up to 6 min. |
| Abracadabrax Clip | Abracadabrax | 30 | — | 30-second song clips with vocals, from one prompt. |
| Abracadabrax Pro | Abracadabrax | 60 | — | Full songs up to 3 minutes with vocals and timed lyrics. |
| Abracadabrax Cover | Abracadabrax | 120 | — | Re-style an existing track, keeping the melody (remix or new lyrics). |
| Abracadabrax Extend | Abracadabrax | 90 | — | Extend a track at the start or end (musical outpainting). |
| Abracadabrax Replace | Abracadabrax | 90 | — | Regenerate a section of a track while keeping the rest (inpaint). |
| Abracadabrax Stems | Abracadabrax | 100 | — | Split a track into vocals, drums, bass and more. |
Try it on every model
New accounts start with a 7-day trial for $1 that includes 140 credits, then the plan you pick renews monthly until you cancel. Each model shows its credit cost before you run it.