Modelli Video

Gemini Omni is Google's multimodal video generation model for creating videos from text, image references, source video, reusable audio assets, and character asset IDs.

Seedance 2.0 is ByteDance's multimodal video model supporting text-to-video, first-and-last-frames, and omni-reference modes. APIXO exclusive: unlimited concurrency, real-person portrait support, and hidden capabilities.

Seedance 2.0 Fast is an APIXO route for ByteDance Seedance 2.0 workflows, exposing text-to-video, first-and-last-frames, and omni-reference modes with optional sound, web search, and 480p/720p output.

HappyHorse is Alibaba's video generation and editing model for text-to-video, image-to-video, reference-guided generation, and video-edit workflows with 720p/1080p output.

Seedance 2.5 is ByteDance's audiovisual video model for longer, reference-driven storytelling. It combines timeline-based direction, multimodal creative guidance, synchronized sound, multilingual performance, and selective revision to help production teams develop connected scenes instead of isolated short clips.

MiniMax H3 is a general-purpose multimodal video model that combines text, image, video, and audio context in one generation workflow. It creates videos up to 2K and 15 seconds with native stereo sound, while supporting first-and-last-frame control, mixed-media references, motion transfer, multi-shot storytelling, and instruction-guided video editing.

Seedance 1.5 Pro is ByteDance's per-second video model for fast text-to-video and image-to-video generation with 480p/720p/1080p output, optional sound, aspect ratio control, and fixed-lens camera stability.

Wan 2.7 is Alibaba's video generation and editing model for text-to-video, image-to-video, reference-guided generation, and video-edit workflows with optional audio input and 720p/1080p output.

Wan 2.6 is Alibaba's multi-mode video generation model for text, image, flash image, reference, and flash reference workflows, with optional audio input and 720p/1080p output.

Sora 2 Pro is OpenAI’s premium video generation model with higher quality output, supporting text-to-video and image-to-video at 720p and 1080p resolutions with flexible durations of 4, 8, or 12 seconds.

Seedance 2.0 Mini is an APIXO lower-cost route for ByteDance Seedance 2.0 workflows, exposing text-to-video, first-and-last-frames, and omni-reference modes with optional sound, web search, and 480p/720p output.

Kling 3.0 Turbo is Kuaishou's fast video generation model for text-to-video and single-image image-to-video workflows with 720p/1080p output and 3-15 second clips.

Hailuo 2.3 is MiniMax's async video model with standard and pro modes for text-to-video and image-to-video generation. Standard mode supports 6s/10s at 768p, while pro mode returns fixed 5s at 1080p.

Hailuo 2.3 Fast is MiniMax's speed-optimized image-to-video model with standard and pro modes. Standard supports 6s/10s at 768p, while pro returns fixed 6s output at 1080p.

Grok Video is xAI's async video generation model for text-to-video and image-to-video workflows, with optional continuation via task_id + index and style control.

Wan 2.2 Animate API is Alibaba's character animation model that combines one source image and one motion video to generate stylized animated outputs with animate/replace behavior.

InfiniteTalk converts one photo plus audio into audio-driven talking or singing avatar videos with precise lip synchronization. Supports up to 10 minutes at 480p or 720p resolution.

Kling 3.0 Std is Kuaishou's standard-quality video generation model with text-to-video, image-to-video, and motion-control modes. It supports clips up to 15 seconds with optional sound generation and flexible aspect ratios.

Vidu Q3 is a per-second video generation model that combines standard and Turbo text-to-video plus image-to-video workflows in one API. It supports single-image animation, first-and-last-frame transitions, optional sound and BGM, and output up to 1080p.

Kling 2.5 Turbo Pro is Kuaishou's high-speed video model for text-to-video and image-to-video creation. It supports 5-10 second clips, optional tail-frame images, aspect ratio control for text-to-video, plus negative prompts and CFG scale guidance.

LTX-2 19B is Lightricks' open-source 19B diffusion transformer for cinematic video generation. It supports text-to-video and image-to-video workflows, LoRA conditioning, and high-fidelity outputs up to 1080p in the API.

Kling 2.1 is Kuaishou's multi-tier video model with Standard, Pro, and Master modes for image-to-video and text-to-video creation. It supports 5-10 second clips, optional tail images for Pro, and aspect ratio control for Master text-to-video.

Kling 2.6 is Kuaishou's native audio-visual video model that generates video, speech, sound effects, and ambience in one pass. It supports text-to-audio-visual and image-to-audio-visual creation with Chinese and English voice generation and up to 10-second clips.

Google DeepMind’s upgraded AI video model with lite, fast, and quality routes, 4/6/8 second duration control, 720p/1080p/4k output, and multi-image reference workflows.

Wan 2.5 is Alibaba's video generation model for text-to-video and image-to-video workflows, with optional audio input, 480p/720p/1080p output, 5 or 10 second clips, and prompt expansion.

Sora 2 is OpenAI’s synchronized short-video generation model on APIXO, supporting text-to-video and single-image-to-video with realistic motion, generated audio, landscape/portrait framing, and 4-, 8-, or 12-second outputs.

FLUX 3 is Black Forest Labs’ multimodal video model for text-to-video, image-to-video, and video extension with native audio and 720p or 1080p MP4 output.

Grok Imagine Video 1.5 is xAI's image-to-video model. It accepts 1–7 reference images and generates 1–15 second videos at 480p, 720p, or 1080p.

Kling 3.0 Omni exposes nine modes through one endpoint: standard, pro, and 4K tiers across text-to-video, image-to-video, and reference-to-video workflows.

MiniMax H3 LoRA is the LoRA-stylized version of MiniMax H3 with 480p and 768p output. Reference images, audio, and video can condition reference-to-video generation.

Wan 3.0 Video supports text-to-video, image-to-video, and reference-to-video workflows with smart duration. Reference mode accepts image, video, audio, file, and link inputs.