# URO API

> One API for image, video and audio generation across every model URO runs. Auth with the x-api-key header, POST /api/models/run-model with a model_id and that model's parameters (or the canonical names), poll GET /api/image-jobs/image-job/{id} or pass webhook_url. Base URL https://client-api.fluxuro.ai/api.

Read the guide first, then the page of the model you want. Every page here is also available as Markdown by replacing .html with .md, and the whole set is in llms-full.txt.

## Docs

- [API guide](https://client-api.fluxuro.ai/docs/guide.md): authentication, run-model, collecting results, uploads, canonical parameters, sizes, pricing modes.
- [All models](https://client-api.fluxuro.ai/docs/models/index.md): index of every active model with price and modes.
- [Model catalogue JSON](https://client-api.fluxuro.ai/docs/models.json): every model with parameters, capabilities and canonical names, machine-readable.
- [Video models compared](https://client-api.fluxuro.ai/docs/models/families/video.md)
- [Nano Banana family](https://client-api.fluxuro.ai/docs/models/families/nano-banana.md)
- [Flux family](https://client-api.fluxuro.ai/docs/models/families/flux.md)

## Audio models

- [ElevenLabs Music](https://client-api.fluxuro.ai/docs/models/elevenlabs-music.md): A short instrumental bed from a plain description, with the length set in milliseconds. Price $0.120.
- [ElevenLabs Sound Effects](https://client-api.fluxuro.ai/docs/models/elevenlabs-sound-effects.md): One sound effect from a description: a door creak, a whoosh, glass breaking, rain on a window, a room tone. Price $0.030.
- [ElevenLabs Voice](https://client-api.fluxuro.ai/docs/models/elevenlabs-voice.md): Text to speech. Price $0.060.
- [Suno Add Instrumental](https://client-api.fluxuro.ai/docs/models/suno-add-instrumental.md): Backing music for a vocal or melody. Price $0.350.
- [Suno Add Vocals](https://client-api.fluxuro.ai/docs/models/suno-add-vocals.md): Sing over an instrumental. Price $0.350.
- [Suno Cover](https://client-api.fluxuro.ai/docs/models/suno-cover.md): Remix: re-record an existing track in a new style while keeping its melody. Price $0.350.
- [Suno Cover Art](https://client-api.fluxuro.ai/docs/models/suno-cover-art.md): Cover images for a Suno song generated through URO, matched to its title and style. Price $0.050.
- [Suno Extend](https://client-api.fluxuro.ai/docs/models/suno-extend.md): Continue a song from a chosen second, keeping its style. Price $0.350.
- [Suno Lyric Timing](https://client-api.fluxuro.ai/docs/models/suno-lyric-timing.md): Word-by-word timestamps for a Suno song generated through URO — for karaoke, captions and lyric videos. Price $0.020.
- [Suno Lyrics](https://client-api.fluxuro.ai/docs/models/suno-lyrics.md): Write song lyrics from a brief, without generating audio. Price $0.030.
- [Suno Mashup](https://client-api.fluxuro.ai/docs/models/suno-mashup.md): Blend two tracks into one new song. Price $0.350.
- [Suno MIDI](https://client-api.fluxuro.ai/docs/models/suno-midi.md): MIDI notes (per instrument) extracted from a Suno Stems job. Price $0.150.
- [Suno Music](https://client-api.fluxuro.ai/docs/models/suno-music.md): Full songs, up to 6 minutes, with real vocals and lyrics (Suno V6). Price $0.350.
- [Suno Music Video](https://client-api.fluxuro.ai/docs/models/suno-music-video.md): An MP4 visualiser of a Suno song generated through URO, with optional artist name and website watermark. Price $0.100.
- [Suno Persona](https://client-api.fluxuro.ai/docs/models/suno-persona.md): Save the singer and style of a Suno song as a reusable persona. Price $0.050.
- [Suno Replace Section](https://client-api.fluxuro.ai/docs/models/suno-replace-section.md): Re-write one part of a song — a verse, a line, a bridge — and keep the rest. Price $0.350.
- [Suno Sound Effects](https://client-api.fluxuro.ai/docs/models/suno-sound-effects.md): A sound effect or short musical sound from Suno, with optional loop, tempo (BPM) and musical key — useful for stingers, loops and game sounds that must sit in a Price $0.120.
- [Suno Stems](https://client-api.fluxuro.ai/docs/models/suno-stems.md): Split a Suno song into separate tracks. Price $0.250.
- [Suno Style Boost](https://client-api.fluxuro.ai/docs/models/suno-style-boost.md): Turn a rough style idea ('pop, mysterious') into a rich style description Suno responds well to. Price $0.020.
- [Suno Voice Create](https://client-api.fluxuro.ai/docs/models/suno-voice-create.md): Step 2 of cloning a singing voice. Price $0.400.
- [Suno Voice Phrase](https://client-api.fluxuro.ai/docs/models/suno-voice-phrase.md): Step 1 of cloning a singing voice. Price $0.100.
- [Suno WAV](https://client-api.fluxuro.ai/docs/models/suno-wav.md): Lossless WAV of a Suno song generated through URO, for mastering or delivery. Price $0.050.

## Background removal models

- [Background Remover](https://client-api.fluxuro.ai/docs/models/background-remover.md): Remove Background from an Image Price ~$0.0008 (recent average).
- [BiRefNet Background Removal](https://client-api.fluxuro.ai/docs/models/birefnet-background-removal.md): BiRefNet (general): cuts the subject out of any image and returns a transparent PNG, with clean edges on hair, fur and glass. Price ~$0.0008 (recent average).
- [Bria RMBG 2.0 Background Removal](https://client-api.fluxuro.ai/docs/models/bria-rmbg-2-0-background-removal.md): Bria RMBG 2.0: a licensed, production-safe background remover with clean edges on complex subjects, trained only on licensed data. Price ~$0.023 (recent average).
- [Ideogram Background Remover](https://client-api.fluxuro.ai/docs/models/ideogram-background-remover.md): Ideogram's background remover: isolates the subject and returns a transparent PNG with minimal haloing and fringing, tuned for graphics, logos and text-heavy im Price ~$0.013 (recent average).
- [RemBG 1.4 Background Removal](https://client-api.fluxuro.ai/docs/models/rembg-1-4-background-removal.md): RemBG 1.4: the classic background remover, $0.0006 and about 5 seconds, with alpha matting for soft edges and an option to return only the mask. Price ~$0.0008 (recent average).

## Image models

- [Bria 3.2](https://client-api.fluxuro.ai/docs/models/bria-3-2.md): Bria 3.2: a commercially licensed text-to-image model trained only on licensed data, with photography or art modes and optional prompt enhancement. Price ~$0.052 (recent average).
- [Bria FIBO](https://client-api.fluxuro.ai/docs/models/bria-fibo.md): Bria FIBO: Bria's newer licensed model built for structured, controllable prompts and precise edits. Price ~$0.052 (recent average).
- [Bria FIBO Edit](https://client-api.fluxuro.ai/docs/models/bria-fibo-edit.md): Bria's FIBO Edit: masked editing on a licensed-safe model, trained only on fully licensed data, for teams that need commercial indemnity. Price ~$0.052 (recent average).
- [Bria FIBO Lite](https://client-api.fluxuro.ai/docs/models/bria-fibo-lite.md): Bria FIBO Lite: the fast tier of FIBO, $0.036 and about 9 seconds, same licensed provenance. Price ~$0.047 (recent average).
- [ERNIE Image](https://client-api.fluxuro.ai/docs/models/ernie-image.md): Baidu's ERNIE-Image: the full-quality ERNIE with steps and guidance, $0.0038 per image. Price ~$0.012 (recent average).
- [ERNIE Image Turbo](https://client-api.fluxuro.ai/docs/models/ernie-image-turbo.md): Baidu's ERNIE-Image Turbo: fast text-to-image with an optional prompt enhancer, strong on Chinese subjects and text. Price ~$0.0025 (recent average).
- [FaceSwap V4](https://client-api.fluxuro.ai/docs/models/faceswap-v4.md): Segmind FaceSwap V4: places the face or head from a source photo onto a target photo, with style matching. Price ~$0.506 (recent average).
- [Fast Flux Schnel](https://client-api.fluxuro.ai/docs/models/fast-flux-schnel.md): Tuned Flux schneel for faster generation but for cost Price ~$0.0034 (recent average).
- [Flux 1 Dev](https://client-api.fluxuro.ai/docs/models/flux-1-dev.md): Flux 1 dev for high-quality image generation Price ~$0.0019 (recent average).
- [Flux 1 Dev Depth](https://client-api.fluxuro.ai/docs/models/flux-1-dev-depth.md): Flux 1 Dev Depth controlnet in the model itself Price ~$0.0060 (recent average).
- [Flux 1 Kontext [Dev]](https://client-api.fluxuro.ai/docs/models/flux-1-kontext-dev.md): FLUX.1 Kontext Dev on Runware: instruction-based image editing (change one thing, keep the rest) from a single reference image, open weights (~$0.02). Price ~$0.015 (recent average).
- [Flux 1 Kontext [MAX]](https://client-api.fluxuro.ai/docs/models/flux-1-kontext-max.md): Flux 1 Kontext Max for high-quality image edit Price ~$0.104 (recent average).
- [Flux 1 Kontext [Pro]](https://client-api.fluxuro.ai/docs/models/flux-1-kontext-pro.md): Black Forest Labs FLUX.1 Kontext Pro: instruction-based editing of one image — change what the prompt says, keep everything else — plus text-to-image (~$0.05). Price ~$0.052 (recent average).
- [Flux 1.1 [pro] Ultra](https://client-api.fluxuro.ai/docs/models/flux-1-1-pro-ultra.md): Black Forest Labs FLUX 1.1 Pro Ultra: high-resolution photoreal text-to-image up to 4MP with excellent prompt adherence (~$0.08). Price ~$0.078 (recent average).
- [FLUX Erase](https://client-api.fluxuro.ai/docs/models/flux-erase.md): FLUX Erase: removes whatever the mask covers and reconstructs the background, no prompt needed. Price ~$0.044 (recent average).
- [FLUX Outpainting](https://client-api.fluxuro.ai/docs/models/flux-outpainting.md): FLUX Outpainting: extends an image by a number of pixels on any side, inventing what lies beyond the frame in the same style. Price ~$0.130 (recent average).
- [Flux Schnell](https://client-api.fluxuro.ai/docs/models/flux-schnell.md): A fast image generation model from Flux family Price ~$0.0011 (recent average).
- [FLUX Virtual Try-On](https://client-api.fluxuro.ai/docs/models/flux-virtual-try-on.md): FLUX Virtual Try-On: dresses the person in one photo with the garment from another, keeping face, body and pose. Price ~$0.081 (recent average).
- [FLUX.1 Fill](https://client-api.fluxuro.ai/docs/models/flux-1-fill.md): FLUX.1 Fill [dev]: inpainting and outpainting. Price ~$0.0042 (recent average).
- [FLUX.1 Fill Pro](https://client-api.fluxuro.ai/docs/models/flux-1-fill-pro.md): Black Forest Labs' FLUX.1 Fill [pro]: the premium inpainter. Price ~$0.065 (recent average).
- [FLUX.1 Krea Dev](https://client-api.fluxuro.ai/docs/models/flux-1-krea-dev.md): FLUX.1 Krea [dev]: Krea's retrain of Flux Dev for photoreal, un-'AI-looking' images with natural light and texture, open weights. Price ~$0.010 (recent average).
- [FLUX.2 [dev]](https://client-api.fluxuro.ai/docs/models/flux-2-dev.md): Experimental developer edition for testing pipelines, structured editing, and multi-input conditioning with full control over parameters and refinement. Price ~$0.012 (recent average).
- [FLUX.2 Flex](https://client-api.fluxuro.ai/docs/models/flux-2-flex.md): FLUX.2 [flex]: the Flux you steer. Price ~$0.078 (recent average).
- [FLUX.2 Klein 4B](https://client-api.fluxuro.ai/docs/models/flux-2-klein-4b.md): Black Forest Labs' FLUX.2 [klein] 4B, the smallest current-generation Flux: text-to-image and reference-image editing in about 4 seconds for $0.0006, the cheape Price ~$0.0008 (recent average).
- [FLUX.2 Klein 9B](https://client-api.fluxuro.ai/docs/models/flux-2-klein-9b.md): Black Forest Labs' FLUX.2 [klein] 9B: text-to-image and image editing in one model, about 4 seconds per image at $0.001. Price ~$0.0016 (recent average).
- [FLUX.2 Max](https://client-api.fluxuro.ai/docs/models/flux-2-max.md): FLUX.2 [max], Black Forest Labs' top quality tier: the most detailed and faithful Flux for hero images and print, with reference-image editing. Price ~$0.091 (recent average).
- [FLUX.2 Pro](https://client-api.fluxuro.ai/docs/models/flux-2-pro.md): FLUX.2 [pro], Black Forest Labs' hosted flagship for production work: text-to-image and multi-reference editing with strong prompt adherence and clean typograph Price ~$0.039 (recent average).
- [Flux1. Expand [pro]](https://client-api.fluxuro.ai/docs/models/flux1-expand-pro.md): FLUX Expand (outpainting): extends an image beyond its edges, filling the new area from the prompt (~$0.06). Price ~$0.065 (recent average).
- [gemini 2.5 Flash (nano banana)](https://client-api.fluxuro.ai/docs/models/gemini-2-5-flash-nano-banana.md): The original Nano Banana (Gemini 2.5 Flash Image): fast image editing and generation with reference images (~$0.05). Price ~$0.055 (recent average).
- [GPT Image 1](https://client-api.fluxuro.ai/docs/models/gpt-image-1.md): OpenAI GPT Image 1: text-to-image and editing with masks and up to 16 reference images (~$0.18). Price ~$0.178 (recent average).
- [GPT Image 1 Mini](https://client-api.fluxuro.ai/docs/models/gpt-image-1-mini.md): OpenAI's GPT Image 1 Mini: the small GPT Image, text-to-image and editing with up to several reference images, quality tiers and transparent backgrounds. Price ~$0.047 (recent average).
- [GPT Image 1.5](https://client-api.fluxuro.ai/docs/models/gpt-image-1-5.md): OpenAI GPT Image 1.5: text-to-image and editing with up to 16 input images, quality tiers and transparent backgrounds (~$0.15). Price ~$0.152 (recent average).
- [GPT Image 2](https://client-api.fluxuro.ai/docs/models/gpt-image-2.md): OpenAI GPT image generation (reverse-engineered channel). Price ~$0.039 (recent average).
- [GPT Image 2.5 Flare](https://client-api.fluxuro.ai/docs/models/gpt-image-2-5-flare.md): OpenAI's fast GPT Image 2.5. Price ~$0.0081 (recent average).
- [GPT Image 2.5 Sunburst](https://client-api.fluxuro.ai/docs/models/gpt-image-2-5-sunburst.md): OpenAI's most capable GPT Image 2.5, for generation and especially editing. Price ~$0.0078 (recent average).
- [Grok Imagine Image](https://client-api.fluxuro.ai/docs/models/grok-imagine-image.md): xAI's Grok Imagine Image: text-to-image and image-to-image with a playful, high-contrast look, $0.02 per image. Price ~$0.026 (recent average).
- [Grok Imagine Image 2.0](https://client-api.fluxuro.ai/docs/models/grok-imagine-image-2-0.md): Grok Imagine Image 2.0: xAI's second generation, up to 3K with a quality setting, editing from reference images and better prompt adherence. Price ~$0.078 (recent average).
- [Grok Imagine Image Quality](https://client-api.fluxuro.ai/docs/models/grok-imagine-image-quality.md): xAI's Grok Imagine Image in quality mode: photoreal text-to-image, or image-to-image from reference images, in about 11 seconds for $0.05. Price ~$0.065 (recent average).
- [HiDream-I1 Dev](https://client-api.fluxuro.ai/docs/models/hidream-i1-dev.md): HiDream-I1 Dev: the 28-step middle tier of HiDream, $0.0045 and about 5 seconds. Price ~$0.0034 (recent average).
- [HiDream-I1 Fast](https://client-api.fluxuro.ai/docs/models/hidream-i1-fast.md): HiDream-I1 Fast: the 16-step distillation of the 17B HiDream text-to-image model, about 4 seconds at $0.004. Price ~$0.0025 (recent average).
- [HiDream-I1 Full](https://client-api.fluxuro.ai/docs/models/hidream-i1-full.md): HiDream-I1 Full: the undistilled 17B HiDream with real guidance, $0.009 and about 10 seconds. Price ~$0.0059 (recent average).
- [Ideogram 3.0](https://client-api.fluxuro.ai/docs/models/ideogram-3-0.md): Ideogram 3.0: the previous Ideogram generation with style presets, a magic-prompt rewriter and character reference images. Price ~$0.078 (recent average).
- [Ideogram 3.0 Edit](https://client-api.fluxuro.ai/docs/models/ideogram-3-0-edit.md): Ideogram 3.0 Edit: masked editing with Ideogram's typography — replace a sign, a label or a menu board and have the new text spelled right. Price ~$0.039 (recent average).
- [Ideogram 3.0 Reframe](https://client-api.fluxuro.ai/docs/models/ideogram-3-0-reframe.md): Ideogram 3.0 Reframe: outpaints an image to a new size and aspect ratio while keeping its style and any text intact, so one hero image becomes every placement. Price ~$0.039 (recent average).
- [Ideogram 3.0 Remix](https://client-api.fluxuro.ai/docs/models/ideogram-3-0-remix.md): Ideogram 3.0 Remix: a new image that keeps the composition of a reference and changes its content, style or branding — the tool for turning one layout into a ca Price ~$0.039 (recent average).
- [Ideogram 3.0 Replace Background](https://client-api.fluxuro.ai/docs/models/ideogram-3-0-replace-background.md): Ideogram 3.0 Replace Background: keeps the subject exactly as photographed and generates a new scene behind it from your description — product on marble, portra Price ~$0.039 (recent average).
- [Ideogram 4.0](https://client-api.fluxuro.ai/docs/models/ideogram-4-0.md): Ideogram 4.0, the typography leader: posters, ads, packaging, thumbnails and any image whose text must be spelled right, in many languages, at 2K. Price ~$0.039 (recent average).
- [Ideogram 4.0 Quality](https://client-api.fluxuro.ai/docs/models/ideogram-4-0-quality.md): Ideogram 4.0 in its quality configuration: the typography leader at its best for posters, packaging and logos where every letter must be right. Price ~$0.078 (recent average).
- [Ideogram 4.0 Remix](https://client-api.fluxuro.ai/docs/models/ideogram-4-0-remix.md): Ideogram 4.0 Remix: Ideogram's latest model applied to an existing image — keep the subject, change everything around it, at 2K with correct text. Price ~$0.039 (recent average).
- [Ideogram Character](https://client-api.fluxuro.ai/docs/models/ideogram-character.md): Ideogram Character: one reference photo locks a character's identity across new scenes, poses and outfits, with optional edit and remix. Price ~$0.078 (recent average).
- [Ideogram Object Remover](https://client-api.fluxuro.ai/docs/models/ideogram-object-remover.md): Ideogram's object remover: masked region gone, background rebuilt, in about 9 seconds for $0.03. Price ~$0.039 (recent average).
- [Imagen 4](https://client-api.fluxuro.ai/docs/models/imagen-4.md): Google Imagen 4: photoreal text-to-image with strong detail and text rendering (~$0.04). Price ~$0.052 (recent average).
- [Imagen 4 Fast](https://client-api.fluxuro.ai/docs/models/imagen-4-fast.md): Google Imagen 4 Fast: photoreal text-to-image with good text rendering at the lowest Imagen price (~$0.02). Price ~$0.026 (recent average).
- [ImagineArt 1.5](https://client-api.fluxuro.ai/docs/models/imagineart-1-5.md): ImagineArt 1.5: a 2K text-to-image model with a polished, commercial look, $0.03 per image. Price ~$0.039 (recent average).
- [ImagineArt 1.5 Pro](https://client-api.fluxuro.ai/docs/models/imagineart-1-5-pro.md): ImagineArt 1.5 Pro: high-resolution text-to-image up to 5K wide, aimed at album covers, posters and print, with good prompt adherence and text. Price ~$0.059 (recent average).
- [ImagineArt 2.0](https://client-api.fluxuro.ai/docs/models/imagineart-2-0.md): ImagineArt 2.0: adds reference-image editing and a reasoning level to ImagineArt, at up to 3K. Price ~$0.039 (recent average).
- [Juggernaut](https://client-api.fluxuro.ai/docs/models/juggernaut.md): An ultra realistic image generation model Price ~$0.0060 (recent average).
- [Juggernaut Z](https://client-api.fluxuro.ai/docs/models/juggernaut-z.md): RunDiffusion's Juggernaut Z: the newest Juggernaut, photoreal people and products with full sampler control and image-to-image. Price ~$0.0076 (recent average).
- [Kandinsky 5.0 Image Lite](https://client-api.fluxuro.ai/docs/models/kandinsky-5-0-image-lite.md): Sber's Kandinsky 5.0 Image Lite: an open-source text-to-image and editing model with a distinct painterly-to-photoreal range, $0.0026 per image. Price ~$0.0066 (recent average).
- [Kling Image 3.0](https://client-api.fluxuro.ai/docs/models/kling-image-3-0.md): Kuaishou's Kling IMAGE 3.0: text-to-image and reference editing at up to 3K with photoreal people and products. Price ~$0.036 (recent average).
- [Kling Image O1](https://client-api.fluxuro.ai/docs/models/kling-image-o1.md): Kling IMAGE O1: Kling's reference-driven image model — give it several images and it composes and edits with strong identity and product consistency. Price ~$0.036 (recent average).
- [Krea 2 Large](https://client-api.fluxuro.ai/docs/models/krea-2-large.md): Krea 2 Large: Krea's top tier, $0.06 and about 35 seconds. Price ~$0.078 (recent average).
- [Krea 2 Medium](https://client-api.fluxuro.ai/docs/models/krea-2-medium.md): Krea 2 Medium: the full-quality Krea 2 with the creativity dial and reference images, $0.03 and about 23 seconds. Price ~$0.039 (recent average).
- [Krea 2 Medium Turbo](https://client-api.fluxuro.ai/docs/models/krea-2-medium-turbo.md): Krea 2 Medium Turbo: Krea's aesthetic photoreal model at its fastest, with a creativity dial and reference images. Price ~$0.019 (recent average).
- [Krea 2 Raw](https://client-api.fluxuro.ai/docs/models/krea-2-raw.md): Krea 2 Raw: the unopinionated Krea 2 with steps, guidance and a negative prompt, $0.015. Price ~$0.019 (recent average).
- [Krea 2 Turbo](https://client-api.fluxuro.ai/docs/models/krea-2-turbo.md): Krea 2 Turbo: the few-step Krea 2 with steps exposed, $0.015. Price ~$0.019 (recent average).
- [Muse Image](https://client-api.fluxuro.ai/docs/models/muse-image.md): Meta's Muse Image: text-to-image and editing with a reasoning level, web and image search for real-world references, at about 2.5 MP. Price ~$0.013 (recent average).
- [Nano Banana (PRO)](https://client-api.fluxuro.ai/docs/models/nano-banana-pro.md): Google's Nano Banana Pro on Runware, addressed by width/height: text-to-image and editing with up to 8 reference images, up to 4K. Price ~$0.224 (recent average).
- [Nano Banana 2](https://client-api.fluxuro.ai/docs/models/nano-banana-2.md): Google Nano Banana 2 on Runware, addressed by width/height: text-to-image and editing with up to 14 reference images, system prompt, temperature and web search. Price ~$0.186 (recent average).
- [Nano Banana 2 (Flash)](https://client-api.fluxuro.ai/docs/models/nano-banana-2-flash.md): Google's latest image generation model with Pro-level image quality, Flash-level speed, 4K output, 14 aspect ratios, and image editing support. Price ~$0.057 (recent average).
- [Nano Banana 2 Lite](https://client-api.fluxuro.ai/docs/models/nano-banana-2-lite.md): Google's fastest, most efficient image model — ~4s per image, ~2.7x faster than Nano Banana 2. Price ~$0.044 (recent average).
- [Nano Banana 2 Lite Economy](https://client-api.fluxuro.ai/docs/models/nano-banana-2-lite-economy.md): Google Nano Banana 2 Lite. Price ~$0.032 (recent average).
- [Nano Banana Pro](https://client-api.fluxuro.ai/docs/models/nano-banana-pro.md): Google Nano Banana Pro via ApiYi: the strongest Nano Banana for editing and composition, up to 8 reference images, 1K to 4K, addressed by aspect_ratio + resolut Price ~$0.080 (recent average).
- [Object Eraser](https://client-api.fluxuro.ai/docs/models/object-eraser.md): Runware's generic object eraser: masks out an object and fills the gap from the surroundings, with an optional prompt describing what should be there instead. Price ~$0.0042 (recent average).
- [P-Image](https://client-api.fluxuro.ai/docs/models/p-image.md): Pruna's P-Image: a distilled, very fast text-to-image model, about 5 seconds at $0.0044, up to 1440px. Price ~$0.0057 (recent average).
- [P-Image Edit](https://client-api.fluxuro.ai/docs/models/p-image-edit.md): Pruna's P-Image-Edit: a distilled, fast instruction editor — background swaps, object and colour changes — in about 7 seconds for under a cent. Price ~$0.011 (recent average).
- [P-Image Ideogram](https://client-api.fluxuro.ai/docs/models/p-image-ideogram.md): Pruna's P-Image in Ideogram style: Ideogram-like typography and design at a tenth of the price, $0.003, with an optional prompt enhancer and reasoning level. Price ~$0.015 (recent average).
- [P-Image Try-On](https://client-api.fluxuro.ai/docs/models/p-image-try-on.md): Pruna's P-Image Try-On: dresses a person in a garment while preserving identity, pose and setting, returned at the input's original size. Price reported after the run.
- [Qwen Image](https://client-api.fluxuro.ai/docs/models/qwen-image.md): Alibaba's Qwen-Image, a 20B open-weight model with the strongest text rendering among open models, in English and Chinese: posters, signage, packaging and UI mo Price ~$0.0066 (recent average).
- [Qwen Image 2.0](https://client-api.fluxuro.ai/docs/models/qwen-image-2-0.md): Alibaba's hosted Qwen-Image 2.0: native 2K generation and editing with reference images, excellent text rendering and an optional prompt expander. Price ~$0.045 (recent average).
- [Qwen Image 2.0 Pro](https://client-api.fluxuro.ai/docs/models/qwen-image-2-0-pro.md): Qwen-Image 2.0 Pro: the higher-quality tier of Qwen 2.0, same controls, about twice the time and price ($0.075). Price ~$0.098 (recent average).
- [Qwen Image 2512](https://client-api.fluxuro.ai/docs/models/qwen-image-2512.md): Qwen-Image 2512, the December refresh of Qwen-Image: better realism and finer text at the same open-weight price ($0.005). Price ~$0.0025 (recent average).
- [Qwen Image 3.0](https://client-api.fluxuro.ai/docs/models/qwen-image-3-0.md): Qwen-Image 3.0: Alibaba's newest hosted image model, text-to-image and editing with a reasoning-style prompt expander. Price ~$0.039 (recent average).
- [Qwen Image 3.0 Pro](https://client-api.fluxuro.ai/docs/models/qwen-image-3-0-pro.md): Qwen-Image 3.0 Pro: the top Qwen tier, $0.04 at 1K and $0.075 at 2K, about a minute per image. Price ~$0.052 (recent average).
- [Qwen Image Edit](https://client-api.fluxuro.ai/docs/models/qwen-image-edit.md): Alibaba's Qwen-Image-Edit, a 20B instruction-following editor: describe the change in words and it edits one image while keeping everything else, including text Price ~$0.013 (recent average).
- [Qwen Image Edit 2511](https://client-api.fluxuro.ai/docs/models/qwen-image-edit-2511.md): Alibaba's Qwen-Image-Edit-2511, the newest Qwen editor: multi-image instruction editing with stronger identity and text fidelity than the original. Price ~$0.014 (recent average).
- [Qwen Image Edit Plus](https://client-api.fluxuro.ai/docs/models/qwen-image-edit-plus.md): Qwen-Image-Edit-Plus: the multi-image version of Qwen's editor. Price ~$0.018 (recent average).
- [Qwen Image Layered](https://client-api.fluxuro.ai/docs/models/qwen-image-layered.md): Qwen-Image-Layered: decomposes one image into separate RGBA layers — subject, background, foreground elements — that can be edited independently, like a PSD fro Price ~$0.037 (recent average).
- [Recraft V4](https://client-api.fluxuro.ai/docs/models/recraft-v4.md): Recraft V4: the previous Recraft generation, same design and text strengths, $0.04. Price ~$0.052 (recent average).
- [Recraft V4.1](https://client-api.fluxuro.ai/docs/models/recraft-v4-1.md): Recraft V4.1: a design-first image model for brand graphics, icons, illustration and layouts with strong text, and control of the palette. Price ~$0.045 (recent average).
- [RiverFlow 1.1](https://client-api.fluxuro.ai/docs/models/riverflow-1-1.md): Sourceful RiverFlow 1.1: a design-oriented image model for editing layouts, packaging and marketing visuals from source images (~$0.05). Price ~$0.050 (recent average).
- [Riverflow 2.0 Fast](https://client-api.fluxuro.ai/docs/models/riverflow-2-0-fast.md): Sourceful's Riverflow 2.0 Fast: design-oriented image generation with reference images for products and styles, at $0.02 per run and about a minute. Price ~$0.026 (recent average).
- [Riverflow 2.5 Fast](https://client-api.fluxuro.ai/docs/models/riverflow-2-5-fast.md): Sourceful's Riverflow 2.5 Fast: a design-native image model for infographics, packaging, layouts and ads, with optional reference images to keep a product or a  Price ~$0.026 (recent average).
- [Runway Gen-4 Image](https://client-api.fluxuro.ai/docs/models/runway-gen-4-image.md): Runway Gen-4 Image: reference-driven generation that keeps characters, objects and locations consistent across images, up to 1080p. Price ~$0.104 (recent average).
- [Runway Gen-4 Image Turbo](https://client-api.fluxuro.ai/docs/models/runway-gen-4-image-turbo.md): Runway Gen-4 Image Turbo: the faster, cheaper Gen-4 Image with the same reference consistency, $0.02 per image. Price ~$0.026 (recent average).
- [SeeDream 4.0](https://client-api.fluxuro.ai/docs/models/seedream-4-0.md): ByteDance SeeDream 4.0: text-to-image and editing with up to 14 reference images at 1K to 4K (~$0.04). Price ~$0.039 (recent average).
- [SeeDream 4.5](https://client-api.fluxuro.ai/docs/models/seedream-4-5.md): ByteDance's SeeDream 4.5: text-to-image and multi-image editing at up to 4K with up to 14 reference images and strong text rendering. Price ~$0.052 (recent average).
- [Seedream 5.0 Lite](https://client-api.fluxuro.ai/docs/models/seedream-5-0-lite.md): ByteDance Seedream 5.0 Lite: the newest Seedream generation with reasoning, up to 3K, and sequential multi-image generation for consistent sets. Price ~$0.045 (recent average).
- [Seedream 5.0 Pro](https://client-api.fluxuro.ai/docs/models/seedream-5-0-pro.md): ByteDance Seedream 5.0 Pro: the flagship Seedream with a planning pass, up to 2K, and reference editing. Price ~$0.063 (recent average).
- [TwinFlow Z-Image Turbo](https://client-api.fluxuro.ai/docs/models/twinflow-z-image-turbo.md): TwinFlow's few-step distillation of Z-Image Turbo: about 2 seconds per image at $0.0006, with most of the original's quality. Price ~$0.0008 (recent average).
- [Wan 2.6 Image](https://client-api.fluxuro.ai/docs/models/wan-2-6-image.md): Wan 2.6 Image: the previous hosted Wan image model, text-to-image and reference editing with a prompt expander. Price ~$0.039 (recent average).
- [Wan 2.7 Image](https://client-api.fluxuro.ai/docs/models/wan-2-7-image.md): Alibaba's Wan 2.7 Image: hosted text-to-image and reference editing at up to 2K with a 'thinking' pass that plans layout and text before drawing. Price ~$0.039 (recent average).
- [Wan 2.7 Image Pro](https://client-api.fluxuro.ai/docs/models/wan-2-7-image-pro.md): Wan 2.7 Image Pro: the 4K-capable tier of Wan 2.7 with the same planning pass and reference editing, $0.075 per image. Price ~$0.098 (recent average).
- [Z-Image](https://client-api.fluxuro.ai/docs/models/z-image.md): Tongyi's Z-Image (base): the full, non-distilled version of Z-Image Turbo. Price ~$0.0075 (recent average).
- [Z-Image Turbo](https://client-api.fluxuro.ai/docs/models/z-image-turbo.md): Tongyi's Z-Image Turbo, a 6B distilled model: photoreal text-to-image in about 3 seconds at $0.0013, with legible English and Chinese text. Price ~$0.0025 (recent average).

## Upscaler models

- [Bria Increase Resolution](https://client-api.fluxuro.ai/docs/models/bria-increase-resolution.md): Bria's licensed, production-safe upscaler: 2x or 4x with fine detail and transparency preserved, trained only on licensed data. Price ~$0.052 (recent average).
- [CCSR Upscale](https://client-api.fluxuro.ai/docs/models/ccsr-upscale.md): CCSR (content-consistent super-resolution): a diffusion 2x upscale that keeps structure and identity stable while restoring detail, guided by an optional prompt Price ~$0.0049 (recent average).
- [Clarity Upscale](https://client-api.fluxuro.ai/docs/models/clarity-upscale.md): Clarity Upscaler: a generative 2x or 4x upscale that adds plausible skin, fabric and surface detail as it enlarges. Price ~$0.0075 (recent average).
- [Image Upscaler](https://client-api.fluxuro.ai/docs/models/image-upscaler.md): Upscale Your image to very high-quality output Price reported after the run.
- [P-Image Upscale](https://client-api.fluxuro.ai/docs/models/p-image-upscale.md): Pruna's P-Image Upscale: a fast AI upscale priced by output size — $0.005 up to 4 MP, $0.01 up to 8 MP, $0.02 up to 16 MP — with optional detail and realism enh Price ~$0.0065 (recent average).
- [Real-ESRGAN Upscale](https://client-api.fluxuro.ai/docs/models/real-esrgan-upscale.md): Real-ESRGAN: a fast, faithful 2x or 4x upscale that sharpens without inventing detail. Price ~$0.0008 (recent average).
- [Recraft Crisp Upscale](https://client-api.fluxuro.ai/docs/models/recraft-crisp-upscale.md): Recraft Crisp Upscale: a clean, fast enlarger for graphics, product shots and UI, at a quarter of a cent per image. Price ~$0.0032 (recent average).
- [SD Latent Upscaler](https://client-api.fluxuro.ai/docs/models/sd-latent-upscaler.md): Stable Diffusion's latent upscaler: a fast 2x enlargement done in latent space before decoding, so detail is sharpened rather than merely interpolated. Price ~$0.0042 (recent average).
- [SwinIR Upscale](https://client-api.fluxuro.ai/docs/models/swinir-upscale.md): SwinIR, a Swin-Transformer restoration model: 2x or 4x super-resolution with strong texture recovery and few artefacts, no prompt needed. Price ~$0.0049 (recent average).
- [Topaz Image Upscale](https://client-api.fluxuro.ai/docs/models/topaz-image-upscale.md): Topaz upscaling: the premium enlarger for photos that must stay sharp at 2x or 4x, with detail recovery rather than blur (~$0.05 up to 2K output, more at 4K and Price ~$0.065 (recent average).
- [Topaz Wonder 3.5 Upscale](https://client-api.fluxuro.ai/docs/models/topaz-wonder-3-5-upscale.md): Topaz Labs Wonder 3.5: the premium generative enhancer, recovering realistic detail from good and degraded sources alike, 2x to 6x, up to 256 megapixels. Price reported after the run.

## Tool models

- [Auto Cropper](https://client-api.fluxuro.ai/docs/models/auto-cropper.md): auto cropper Price ~$0.0086 (recent average).
- [Combine Images  (for redux)](https://client-api.fluxuro.ai/docs/models/combine-images-for-redux.md):  Price ~$0.0001 (recent average).
- [preProcess Image (CNet)](https://client-api.fluxuro.ai/docs/models/preprocess-image-cnet.md): Preprocess an image for control net guide image Price ~$0.0017 (recent average).
- [Resize Image](https://client-api.fluxuro.ai/docs/models/resize-image.md): Resize an image to provided dimensions Price ~$0.0001 (recent average).

## Video models

- [Gemini Omni Flash](https://client-api.fluxuro.ai/docs/models/gemini-omni-flash.md): Google's multimodal video generation and editing model with native audio generation. Price ~$0.847 (recent average).
- [Google Veo 3](https://client-api.fluxuro.ai/docs/models/google-veo-3.md): Googles Cutting edge video generation model Price ~$2.080 (recent average).
- [Google Veo 3 fast](https://client-api.fluxuro.ai/docs/models/google-veo-3-fast.md): Google Veo 3 Fast: 8 second 1080p clips with optional generated audio (speech, effects, ambience) from text or a first frame. Price ~$1.196 (recent average).
- [Grok Imagine Video](https://client-api.fluxuro.ai/docs/models/grok-imagine-video.md): xAI's multimodal video model that generates short clips with native synchronized audio from text or images. Price ~$0.437 (recent average).
- [HappyHorse 1.1](https://client-api.fluxuro.ai/docs/models/happyhorse-1-1.md): Alibaba's multimodal I2V model with stronger motion continuity, multi-image reference consistency, facial texture quality, and character stability. Price ~$0.874 (recent average).
- [Kling 2.1](https://client-api.fluxuro.ai/docs/models/kling-2-1.md): Using Klings Latest video generation model to bring creativity to life Price ~$1.105 (recent average).
- [Kling 2.1 Master](https://client-api.fluxuro.ai/docs/models/kling-2-1-master.md): Kling 2.1 Master: Kling's top 2.1 tier, 5 or 10 second 1080p clips from text or a first frame (~$1.20). Price ~$1.201 (recent average).
- [Kling Squish](https://client-api.fluxuro.ai/docs/models/kling-squish.md): Kling's squish effect: turns the subject of one image into a short 'squish' clip. Price ~$0.728 (recent average).
- [Kling Video 3.0 4K](https://client-api.fluxuro.ai/docs/models/kling-video-3-0-4k.md): Kling VIDEO 3.0 4K variant. Price ~$2.730 (recent average).
- [Kling VIDEO O1 Pro](https://client-api.fluxuro.ai/docs/models/kling-video-o1-pro.md): Kling O1 Pro: unified multimodal video foundation model for controllable generation and instruction-based editing. Price ~$0.764 (recent average).
- [Kling Video O3 4K](https://client-api.fluxuro.ai/docs/models/kling-video-o3-4k.md): Kling VIDEO O3 4K variant. Price ~$6.006 (recent average).
- [KlingAI 2.5 Turbo PRO](https://client-api.fluxuro.ai/docs/models/klingai-2-5-turbo-pro.md): Kling 2.5 Turbo (pro): first-frame or first-and-last-frame video, 5 or 10 seconds, higher quality than standard (~$0.45). Price ~$0.455 (recent average).
- [KlingAI 2.5 Turbo Standard](https://client-api.fluxuro.ai/docs/models/klingai-2-5-turbo-standard.md): Kling 2.5 Turbo (standard): image-to-video from one first frame, 5 or 10 seconds, at the lowest Kling price (~$0.30). Price ~$0.300 (recent average).
- [LTX 2.3](https://client-api.fluxuro.ai/docs/models/ltx-2-3.md): Lightricks multimodal video model with native synchronized audio. Price ~$1.196 (recent average).
- [LTX-2](https://client-api.fluxuro.ai/docs/models/ltx-2.md): Lightricks LTX-2: the cheapest video model here (~$0.07), 1 to 19 seconds from text or a first frame, with steps, fps and cfg exposed. Price ~$0.067 (recent average).
- [Luma Ray 2 Flash](https://client-api.fluxuro.ai/docs/models/luma-ray-2-flash.md): Luma's fast Ray 2 video model: 5 or 9 second clips from text or a first frame at 540p to 4K. Price ~$0.0000 (recent average).
- [MiniMax H3](https://client-api.fluxuro.ai/docs/models/minimax-h3.md): MiniMax H3: multimodal video generation with native synchronized audio, multi-reference consistency (images, videos, audios), and continuation workflows. Price ~$1.251 (recent average).
- [MiniMax H3 Max](https://client-api.fluxuro.ai/docs/models/minimax-h3-max.md): Performance-tuned MiniMax H3 variant built for fast video generation. Price ~$0.780 (recent average).
- [PixVerse V6](https://client-api.fluxuro.ai/docs/models/pixverse-v6.md): Multi-shot cinematic video with native synchronized audio, 20+ camera controls, character consistency across shots. Price ~$0.332 (recent average).
- [Seedance 1.0 Pro](https://client-api.fluxuro.ai/docs/models/seedance-1-0-pro.md): ByteDance Seedance 1.0 Pro: 3 to 12 second clips from text or a first frame with a camera-lock option (~$0.77). Price ~$0.767 (recent average).
- [Seedance 2.0](https://client-api.fluxuro.ai/docs/models/seedance-2-0.md): ByteDance unified multimodal video model. Price ~$2.507 (recent average).
- [Seedance 2.0 Fast](https://client-api.fluxuro.ai/docs/models/seedance-2-0-fast.md): ByteDance speed-optimized multimodal video model. Price ~$0.849 (recent average).
- [Seedance 2.5](https://client-api.fluxuro.ai/docs/models/seedance-2-5.md): ByteDance production-grade multimodal video model. Price ~$3.800 (recent average).
- [Veo 3.1](https://client-api.fluxuro.ai/docs/models/veo-3-1.md): Google Veo 3.1 on Runware: 4, 6 or 8 second clips at 720p/1080p with native audio, first/last frame images and up to 3 reference images. Price ~$4.160 (recent average).
- [VEO 3.1](https://client-api.fluxuro.ai/docs/models/veo-3-1.md): Google VEO 3.1 — AI video generation. Price ~$0.325 (recent average).
- [VEO 3.1 Fast](https://client-api.fluxuro.ai/docs/models/veo-3-1-fast.md): Google VEO 3.1 Fast — faster, more affordable AI video. Price reported after the run.
- [Video Loop](https://client-api.fluxuro.ai/docs/models/video-loop.md): Turns a clip into a seamless loop by cross-fading its end into its start. Price ~$0.0004 (recent average).
- [Wan 2.2](https://client-api.fluxuro.ai/docs/models/wan-2-2.md): Alibaba Wan 2.2 on Runware: open-weight video model, 5 or 8 seconds, text or first/last frame, tunable steps, fps and cfg. Price ~$0.432 (recent average).
- [Wan 2.7](https://client-api.fluxuro.ai/docs/models/wan-2-7.md): Alibaba next-gen multimodal video model. Price ~$0.628 (recent average).

## Optional

- [llms-full.txt](https://client-api.fluxuro.ai/docs/llms-full.txt): the guide and every model page in one file.