Models and prices
Every model in the studio in one list: what each one does, its key features and the price of one generation in tokens.
Images
Generation from a description and editing of your own photos. The price is per image; for many models it depends on the resolution or quality.
-
Nano Banana 2
The go-to model for most tasks — posts, illustrations, images with crisp in-image text, up to 14 reference images per request 1K, 2K, 4K · 14 aspect ratios · up to 14 references from 2 t -
Nano Banana Pro
For complex compositions, infographics, and precise in-image text at 2K/4K — final assets for advertising and print 1K, 2K, 4K · 11 aspect ratios · up to 8 references from 5 t -
Flux 2
Photorealistic product shots, ad scenes, and precise edits to existing images without redrawing from scratch 1K, 2K · 8 aspect ratios · up to 8 references from 2 t -
GPT Image 2
Realistic photos, packaging, and UI mockups with precise typography and dense in-image text 11 aspect ratios · up to 16 references 3 t -
Grok Imagine
A distinctive artistic look for covers, social posts, and creative ideas — when you want to break out of the default style 3 aspect ratios · up to 1 reference 2 t -
Seedream 4
Fast series in one consistent style — storyboards, covers, up to 6 variants per request in 2K/4K 1K, 2K, 4K · 9 aspect ratios · up to 10 references 2 t -
Nano Banana
The base model for drafts, sketches, and quick edits — when you need lots of iterations 11 aspect ratios · up to 10 references 1 t -
GPT Image 1.5
Product cards, posters, and text-heavy infographics — bulk generation in your brand style 3 aspect ratios · up to 16 references from 2 t -
Qwen Image
Posters, covers, and packaging with multilingual in-image text — English, Chinese, and more 5 aspect ratios · up to 1 reference 1 t -
Z-Image
Product cards and marketplace mockups — tidy compositions and clean product scenes 6 aspect ratios · up to 1 reference 1 t -
Seedream 5
Three versions to choose from — fast Flash, thoughtful Lite, and precise Pro for infographics and edits 1K, 1.5K, 2K, 3K, 4K · 8 aspect ratios · up to 14 references from 1 t -
Nano Banana 2 Lite
The fastest, most affordable model in the Nano Banana family — drafts, ideas, and text-driven image edits 15 aspect ratios · up to 10 references 1 t -
GPT Image 2.5
Sharp detail, natural light, and precise edits — in fast Flare and premium Sunburst 1K, 2K, 4K · 9 aspect ratios · up to 16 references from 3 t -
Imagen 4
Photorealistic images from Google DeepMind with fine detail and crisp text — in three variants tuned for speed or quality 6 aspect ratios · up to 1 reference from 1 t -
Grok Imagine 2.0
The next generation of xAI's model — follows complex prompts more closely, handles text cleanly, and edits images with care 6 aspect ratios · up to 5 references 1 t -
Qwen Image 3
Rich layouts, infographics, and small in-image text in 12 languages — in Standard and Pro 1K, 2K · 8 aspect ratios · up to 3 references from 2 t -
Ideogram V3
Logos, posters, and brand graphics with clean typography — from quick draft to final 5 aspect ratios · up to 1 reference from 1 t -
Ideogram Character
One character in any scene or style — from a single reference 5 aspect ratios · up to 1 reference from 3 t -
Wan 2.7 Image
Generation and editing in one model — up to 9 sources, text in 12 languages, up to 2K 1K, 2K · 8 aspect ratios · up to 9 references from 2 t -
Recraft — Background Removal
Precise background removal on tricky edges — hair, fur, sheer fabrics. Outputs a transparent PNG up to 1 reference 1 t -
Recraft Crisp Upscale
Upscale a finished frame up to 4x with added sharpness and detail — no scene regeneration up to 1 reference 1 t -
Topaz Image Upscale
Upscale up to ×4 with detail recovery — removes blur, noise, and compression artifacts ×1, ×2, ×4 · up to 1 reference from 3 t
Video
Clips from a description, from a first frame and from references. The price is per clip: it grows with length and resolution, and sound costs more.
-
Kling 2.6
5–10 second videos with speech, effects, and ambient sound — for ads and social media 5–10 sec · 3 aspect ratios · up to 1 reference · sound from 8 t -
Seedance 2.0
Cinematic video up to 15 seconds in 1080p — natural motion physics and synced audio 4–15 sec · 480p, 720p, 1080p · 7 aspect ratios · up to 15 references from 16 t -
Kling 3.0
3–15 second video in 720p and 1080p with native audio — plus fast Turbo and reference-driven Omni 3–15 sec · 720p, 1080p · 4 aspect ratios · up to 7 references · sound from 12 t -
Seedance 2.5
Video up to 30 seconds in 1080p — longer scenes, precise reference control, and synced audio 4–30 sec · 480p, 720p, 1080p · 7 aspect ratios · up to 50 references from 28 t -
Seedance 2.0 Mini
Fast, low-cost video up to 15 seconds — Seedance 2.0 Fast–level quality for high-volume work 4–15 sec · 480p, 720p · 7 aspect ratios · up to 15 references from 4 t -
Grok Video
Short clips with the signature Grok aesthetic — for teasers and offbeat social media inserts 6–30 sec · 480p, 720p · 5 aspect ratios · up to 7 references from 3 t -
Grok Video 1.5
Brings images to life with realistic motion and built-in sound 2–15 sec · 480p, 720p · 6 aspect ratios · up to 7 references from 1.2 t -
Wan 3.0
Clips up to 30 seconds with sound — from text, first and last frames, or references 2–30 sec · 480P, 720P, 1080P · 6 aspect ratios · up to 10 references · first and last frame from 4 t -
MiniMax H3
Up to 2K video with stereo sound — from text, frames, or references 4–15 sec · 768P, 2K · 7 aspect ratios · up to 5 references · first and last frame from 8 t -
Wan 2.7 Video
720p and 1080p video from text, frames, or multiple references 2–15 sec · 720p, 1080p · 5 aspect ratios · up to 5 references · first and last frame from 8 t -
Hailuo 2.3
Turns an image into a 6- or 10-second clip — realistic motion and lifelike facial expressions 6–10 sec · 768P · up to 1 reference from 8 t -
HappyHorse 1.1
Videos up to 15 seconds from text, an image, or several references — with consistent characters 3–15 sec · 720p, 1080p · 9 aspect ratios · up to 9 references from 18 t -
PixVerse V6
Cinematic video up to 15 seconds in 1080p — with native audio and consistent characters 4–15 sec · 360p, 720p, 1080p · 8 aspect ratios · up to 1 reference · sound from 4 t -
Gemini Omni 1.1 Flash
Video from fast 360p drafts up to 4K — from text and up to 7 reference images 4–10 sec · 360p, 720p, 1080p, 4k · 2 aspect ratios · up to 7 references from 16 t
AI chat
Language models for writing, code, and going through documents and photos. An answer is billed by what it actually used; below is the approximate price of one answer.
-
Claude Opus 5.5
The smartest: hard tasks, code, long texts 0.3 t -
Claude Sonnet 5.5
Smart and fast: writing, code, analysis 0.2 t -
GPT-6 Sol
OpenAI's strong all-round model 0.1 t -
GPT-6 Luna
Fast and very cheap 0.1 t -
Gemini 3.8 Flash
Google's fast model 0.1 t -
Grok 4.7
xAI's model: reasoning and code 0.1 t -
DeepSeek V4.1 Flash
Fast and cheap, text only 0.1 t
Music
Songs, covers, stems and your own voice on Suno V6, Suno V6 Mini, Suno V6 Wild. The price is per operation; these are the main ones, the full list is on the music page.
-
Song
Two versions of a song from a description or from your own lyrics and style. 3 t -
Cover in another style
The same melody in a new style, two versions. 3 t -
Extend
Continues the track from the chosen second, two versions. 3 t -
Replace section
Regenerates a part of the track: at least 10 seconds and no more than half of it. 1.3 t -
Split your track
Your recording split into stems: vocals and instrumental, all instruments, or one chosen stem. File up to 20 MB, it will appear in the library. from 2.5 t -
Sounds and loops
Sound effects, ambience and loops from a description. 0.7 t