Model catalogue

GPT Image 2.5

OpenAI visual model with two rendering styles, an optional transparent background, and up to 4K output.

Nano Banana

Google visual model for fast image generation and reference-based editing.

Nano Banana 2

Second-generation Google visual model with a Lite tier for fast generations and a Standard tier up to 4K resolution.

Nano Banana 2.1

Google's successor to Nano Banana 2 for making and editing images up to 4K, cheaper at every resolution.

Nano Banana Pro

Google visual model for complex prompts, photographic detail, and character consistency across generations.

Seedream 4

ByteDance visual model with versatile aspect ratios and rendering support up to 4K resolution.

Seedream 4.5

ByteDance 4.5 visual model with refined texture detail and multi-tiered quality presets.

Seedream 5

ByteDance visual model with a fast Lite tier, a Pro tier for precise composition, a low-cost Flash tier, and Layer tiers that split an image into separate layers.

GPT Image 1.5

OpenAI visual model with guided text prompt adherence and dual rendering quality settings.

GPT Image 2

Second-generation OpenAI visual model with in-image typography, wide aspect ratios, and up to 4K output.

Grok Imagine Image 2

Second-generation xAI visual model for text prompts and multi-asset editing with up to five reference images.

Grok Imagine Image

Lightweight xAI visual model for rapid text-to-image rendering with optional single image reference.

Wan 2.7 Image

Alibaba visual model with Standard and Pro tiers for output up to 4K, accepting up to nine reference images per prompt.

Qwen 3

Alibaba image model across Standard and Pro tiers up to 2K, supporting composition workflows from up to 3 reference images.

Qwen 2

Fast Alibaba image model for drafting from compact prompts and instruction-based single-image editing.

Qwen 2.1

Alibaba image model up to 2K resolution featuring optional alpha transparency and blending across up to 10 reference images.

Z-Image

Lightweight Alibaba image model producing photorealistic output from text prompts at maximum cost efficiency.

Recraft Remove Background

Automated Recraft cutout tool that isolates main subjects onto a clean transparent alpha layer.

Recraft Crisp Upscale

Recraft upscaler that enhances image resolution, reconstructing crisp edge detail and fine texture fidelity.

Kling 3

Kuaishou video model for 3 to 15-second clips with native audio, up to five scenes, a starting frame, and output up to 4K.

Wan 3 Video

Alibaba video model for 2 to 30-second clips across Standard and Prime tiers, featuring built-in audio and multi-modal media references.

Seedance 1

ByteDance video model producing 5 to 10-second motion animations from text or image prompts across Lite, Fast, and Pro tiers.

Seedance 1.5 Pro

ByteDance video model supporting clips up to 12 seconds with start-and-end frame transitions and audio.

Seedance 2

Second-generation ByteDance video model with three speed tiers, clips up to 15 seconds, and references from images, video, or audio.

Seedance 2.5

ByteDance video model supporting clips up to 30 seconds, long prompts, and image references from up to 30 files.

Kling 3 Turbo

High-speed, cost-efficient Kuaishou video model for 3 to 15-second clips up to 1080p from text or a single reference image.

Kling 3 Motion Control

Kuaishou motion transfer model that maps movement from a reference video onto a character in a still image.

Kling 2.6

Kuaishou video model for 5 or 10-second clips from text or image prompts, with optional native audio.

Grok Imagine Video 1.5

xAI video model for 1 to 15-second clips from text prompts or up to seven reference images per run.

Grok Imagine Video

xAI video model for 6 to 30-second clips from text or up to seven reference images, with output up to 1080p.

Wan 2.7 Video

Alibaba video model supporting four workflows: text-to-video, frame animation, existing video editing, and reference composition.

Wan 2.6 Video

Alibaba video model for 5 to 15-second clips from text, a single image, or the subject of reference videos, with a Standard tier that always has sound and a cheaper Flash tier.

Happy Horse 1

Alibaba video model supporting four workflows: text-to-video, first frame animation, multi-reference, and video editing.

Happy Horse 1.1

Alibaba 1.1 video model featuring reduced per-second rates, nine aspect ratios, and directed motion workflows.

MiniMax H3

MiniMax video model rendering up to 2K resolution (4 to 15 seconds) from text, keyframes, or multi-modal references.

Veo 3.1

Cinematic Google video model up to 4K with built-in audio, in three tiers: Lite for the lowest price, Fast for balance, Quality for the sharpest result.

Vidu Q4

ShengShu's Vidu video model for 3 to 16-second clips up to 4K, from one first frame or up to 15 reference images, with built-in dialogue and sound effects.

Gemini 3.8 Flash TTS

Google's speech model that turns text into spoken audio, with 70 voices for a single narrator or a two-speaker dialogue, on Flash and Flash Lite tiers.