All Models
Browse all available AI models — compare pricing, features, and start integrating.
Kling 4.0 is Kuaishou's flagship video model. One request makes a 3-30 second clip at 720p or 1080p, always with a stereo audio track. Text / Reference mode takes a prompt plus up to 10 images, 5 videos (30s in total) and 3 audio clips, mentioned as @Image1, @Video1, @Audio1. Frames mode animates from a first frame through up to 8 middle frames to an optional last frame. Edit changes an uploaded clip and can keep its sound; Extend continues a clip and returns the full video. Aspect ratios 16:9, 9:16, 1:1 and 21:9. No 4K, negative prompt or silent output.
Muse Video Ext makes one 10-second, 720p clip with native audio per request, from text alone or from up to 9 reference images (11 MiB in total). Pick one of seven aspect ratios, or leave it on auto to follow the references. Write [Shot N] At 00:0x.000 in the prompt to cut between scenes; cuts land within a fraction of a second, but a person may look different after a cut, so keep to two cuts or fewer. No reference video, audio, or first/last frame control.
FLUX 3 Max is a post-trained FLUX 3 Video model from Black Forest Labs, tuned for stronger prompt adherence and visual quality at lower latency. Generate 5 to 20 second videos at 720p or 1080p with native audio from a text prompt, a first frame with an optional last frame, or up to 10 keyframes. Billed per output second.
Vidu Q4 animates a single first-frame image, or combines 1–15 reference images with up to 3 reference audio clips, into 3–16 second videos at 540p, 720p, 1080p, 2K or 4K. It generates synchronized dialogue and sound effects by default and is billed per output second.
Gemini Omni 1.1 Flash Ext generates 4, 6, 8, or 10 second clips at 720p, 1080p, or 4K. Separate from gemini_omni_flash_ext.
Create 2K MiniMax H3 videos from prompts, first/last-frame inputs, or multimodal references through AIReiter.
Gemini Omni Flash Ext generates 4, 6, 8, or 10 second clips at 720p, 1080p, or 4K from a prompt, one first-frame image, one or three reference images, or a single reference video. It is not the official token-billed Omni Flash SKU on this site.
A unified multimodal video generation model with stronger prompt adherence and visual consistency, enabling director-level control over performance, lighting, and camera movement.
A unified multimodal video generation model with stronger prompt adherence and visual consistency, enabling director-level control over performance, lighting, and camera movement.
Professional-grade video generation with smooth motion and cinematic realism.
Lightweight video generation with fast speed, ideal for quick previews and creative exploration.
Comprehensively powerful, uniquely equipped with multi-camera narrative capabilities, and supports first and last frames.
High-precision audio-visual synchronization, film-grade motion and emotional expression, and support for first and last frames.
Create 3-15 second 720p or 1080p videos while linking people, objects, clothing, props, and scenes to [Image N] references.
Generate 3-15 second videos in four workflows, or edit an existing video while preserving its source timing and framing.
Seedance 2.5 upgrades multimodal video generation: extend duration up to 30s, accept up to 30 reference images, 10 reference videos and 10 reference audios. New MOV output format with yuv444p color precision for better color consistency in extension and splicing tasks.
Kling 3.0 Motion Control Video Generator — upload a subject image and a reference clip, and Kling 3.0 transfers the motion onto your subject to produce smooth, controllable video in seconds.
Kling 3.0 Turbo Video Generator — turn text prompts or a single image into 3–15 second clips at 720p or 1080p, with fast turnaround for quick iteration.
Kling 3.0. Text-to-video and image-to-video at 720p/1080p/4K, 3-15s, with optional native audio.
xAI Grok Imagine 1.5 Preview. Turn a static image into a dynamic 6-30s video at 480p or 720p.
FLUX 3 Video supports text-to-video, 1-10 ordered image keyframes, video extension, HD or FHD output, and synchronized native audio.
Kling v3 Omni generates 3–15 second clips at 720p, 1080p, or 4K from a prompt, up to 7 reference images, first/last frames, or one reference video. Optional native audio on text and image modes.
Wan 3.0 generates 2–30 second videos at 480p, 720p, or 1080p from a prompt, first/last frames, or mixed image, video, audio, document, and webpage references. Native audio is on by default.
Seedance 2.0 Mini delivers Seedance 2.0–level quality at roughly half the cost — built for high-volume video: e-commerce content, marketing assets, UGC, and special effects.