All Models
Browse all available AI models — compare pricing, features, and start integrating.
HappyHorse 1.0 supports text-to-video, first-frame image-to-video, reference-to-video with up to nine ordered character images, and prompt-based video editing with optional image references.
HappyHorse 1.1 creates videos from one to nine reference images. Reference individual subjects with [Image 1], [Image 2], and similar markers in the prompt. It supports 720p and 1080p output, nine aspect ratios, and durations from 3 to 15 seconds.
Professional-grade video generation with smooth motion and cinematic realism.
Professional-grade video generation with smooth motion and cinematic realism.
Lightweight video generation with fast speed, ideal for quick previews and creative exploration.
Advanced text-to-video model focused on storytelling and dynamic scenes.
Premium video generation with higher fidelity, longer clips, and cinematic control.
Comprehensively powerful, uniquely equipped with multi-camera narrative capabilities, and supports first and last frames.
Prices hit the bottom, performance reaches the top, inheriting the core advantages of Seedance 1.0 Pro
High-precision audio-visual synchronization, film-grade motion and emotional expression, and support for first and last frames.
A unified multimodal video generation model with stronger prompt adherence and visual consistency, enabling director-level control over performance, lighting, and camera movement.
Gemini Omni Flash on EvoLink uses separate task model keys for text-to-video, image-to-video, reference-to-video, and video-edit, supporting prompt, reference image, and reference video workflows for 720p video generation.
FLUX 3 Video supports text-to-video, 1-10 ordered image keyframes, video extension, HD or FHD output, and synchronized native audio.
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.
Create high-quality 2K videos with MiniMax H3, supporting text-to-video, first/last-frame image-to-video, and multimodal reference-to-video.