THE MODEL CATALOG

Video model APIs & pricing

Find text-to-video, image-to-video and video processing APIs by task. Compare Wan versions, inspect each model’s parameters and submit asynchronous jobs with one Jevrouter key.

586 models · Page 5 of 13

jev

davinci magihuman · text to video

daVinci MagiHuman is a 15B parameter omni video generation model — the new open-source king on par with WAN 2.5. Generates high-quality AI videos from text prompts with optional audio input. Supports digital humans, talking heads, and general video generation.

Video
Per video · quoted before submission
jev

depth anything v3 · video

Depth Anything V3 Video turns any video into a temporally consistent depth map video. Depth stays stable across the whole clip with no flicker or brightness pumping, ideal for replicating camera moves and motion with depth-controlled video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

depth anything · video

Depth Anything Video estimates temporally consistent depth maps from video input, with stable depth across the whole clip and no flicker. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

face enhancer · video

Video Face Enhancer restores and sharpens up to three faces in every frame of a video, with stable, flicker-free results and the original audio kept. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

flashvsr

FlashVSR is a fast, high-quality video upscaler that boosts resolution and restores clarity for low-resolution or blurry footage. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ghibli filter · video

wavespeed-ai/ai-ghibli-filter-video

Video
Per video · quoted before submission
jev

hunyuan avatar

Hunyuan Avatar creates audio-driven talking or singing videos from one image + audio, in 480p/720p up to 120s (starts at $0.15/5s). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

hunyuan video 1.5 · image to video

HunyuanVideo-1.5 (i2v) is a lightweight 8.3B parameter image-to-video model that generates high-quality videos from images with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

hunyuan video 1.5 · text to video

HunyuanVideo-1.5 (t2v) is a lightweight 8.3B parameter text-to-video model that generates high-quality videos with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

hunyuan video · Image to Video

Hunyuan i2v turns images and text prompts into high-quality videos, generating coherent short clips from descriptive inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

hunyuan video · Text to Video

Hunyuan Video (t2v) is an advanced text-to-video model that generates high-quality videos from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk fast · multi

InfiniteTalk fast multi converts a single image and two audio inputs into multi-character talking or singing videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk fast

InfiniteTalk fast converts one photo + audio into audio-driven talking or singing avatar videos (Image-to-Video), up to 10 minutes. Ready-to-use REST API, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk fast · video to video multi

InfiniteTalk fast video-to-video multi converts a video and two audio inputs into multi-character talking or singing videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk fast · video to video

Audio-driven infinitetalk-fast turns one video plus audio into realistic talking or singing videos with lip-sync. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk · multi

InfiniteTalk Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk

InfiniteTalk converts one photo + audio into audio-driven talking or singing avatar videos (Image-to-Video), up to 10 minutes, 720p tier $0.30/5s. Ready-to-use REST API, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk · video to video multi

InfiniteTalk Video-to-Video Multi converts a video and two audio inputs into multi-character talking or singing videos at up to 720p. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

infinitetalk · video to video

Audio-driven InfiniteTalk turns one video plus audio into realistic talking or singing videos with lip-sync in 480p or 720p. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

latentsync

LatentSync synchronizes video and audio inputs to generate seamless synchronized content. Perfect for lip-syncing, audio dubbing, and video-audio alignment tasks.

Video
Per video · quoted before submission
jev

longcat avatar 1.5 · multi

LongCat Avatar 1.5 Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p, capped at 64 seconds per clip. Ready-to-use REST API, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

longcat avatar 1.5

LongCat Avatar 1.5 is the upgraded version of LongCat Avatar with sharper lip sync and faster generation. Converts one photo + audio into audio-driven talking or singing avatar videos (Image-to-Video), capped at 64 seconds per clip. Ready-to-use REST API, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

longcat avatar 1.6 · multi

LongCat Avatar 1.6 Multi turns one image of two people plus two audio tracks into a multi-character talking or singing video, with more natural expressions and steadier long clips than 1.5. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

longcat avatar 1.6

LongCat Avatar 1.6 turns one photo plus audio into a talking or singing avatar video, with more natural expressions and gestures and steadier identity and lighting over long clips than 1.5 (Image-to-Video). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

longcat avatar

LongCat Avatar produces super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity. Converts one photo + audio into audio-driven talking or singing avatar videos (Image-to-Video), up to 2 minutes, 720p tier $0.30/5s. Ready-to-use REST API, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx 2 19b · control

LTX-2 19B ControlNet generates synchronized audio-video (up to 20s) from video input with pose, depth, or canny edge guidance. Supports audio preservation, generation, or removal for flexible video transformation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx 2 19b · image to video LoRA

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access. This version supports custom LoRAs for style personalization.

Video
Per video · quoted before submission
jev

ltx 2 19b · image to video

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2 19b · lipsync

LTX-2 Lipsync is an audio-driven digital human model that generates synchronized talking head videos from a reference image and audio input. It leverages the LTX-2 19B DiT architecture to produce high-fidelity lip-synced videos with natural head movements.

Video
Per video · quoted before submission
jev

ltx 2 19b · text to video LoRA

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access. This version supports custom LoRAs for style personalization.

Video
Per video · quoted before submission
jev

ltx 2 19b · text to video

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2 19b · video upscaler

LTX-2 19B Video Upscaler converts low-resolution videos into crisp 4K footage with seamless motion dynamics and frame consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx 2.3 · image to video LoRA

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2.3 · image to video

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2.3 · lipsync

LTX-2.3 Lipsync is an audio-driven digital human model that generates synchronized talking head videos from a reference image and audio input. It leverages the LTX-2.3 19B DiT architecture to produce high-fidelity lip-synced videos with natural head movements.

Video
Per video · quoted before submission
jev

ltx 2.3 spicy · image to video LoRA

LTX 2.3 Spicy LoRA converts a reference image and prompt into expressive video with selectable LoRA presets, optional LoRA strength overrides, duration, and resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx 2.3 spicy · image to video

LTX 2.3 Spicy converts a reference image and prompt into expressive video with selectable style preset, duration, and resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx 2.3 · text to video LoRA

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2.3 · text to video

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access.

Video
Per video · quoted before submission
jev

ltx 2.3 · video extend

LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.

Video
Per video · quoted before submission
jev

ltx 2.5 · image to video

LTX-2.5 animates a first-frame image into synchronized audio-video content, with optional last-frame guidance and resolutions up to 4K.

Video
Per video · quoted before submission
jev

ltx 2.5 · text to video

LTX-2.5 generates synchronized audio-video content from text prompts with high-fidelity motion, flexible duration, and resolutions up to 4K.

Video
Per video · quoted before submission
jev

ltx video v097 · Image to Video 480p

Generate 480p videos from text prompts and images with LTX Video 0.9.7 (i2v-480p). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

ltx video v097 · Image to Video 720p

Generate 720p videos from text prompts and images with LTX Video-0.9.7 for consistent, high-quality image-to-video results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

lynx

Lynx by ByteDance converts images into subject-consistent videos, preserving visual consistency across frames for seamless animations and reliable subject fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

magi 1 24b

Magi-1 is a cinematic video generation model with strong understanding of physical interactions and cinematic prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

minimax h3 · controlnet union

MiniMax H3 Open Weights ControlNet Union generates a new video that follows the motion and composition of a source video. Pose, depth, edges, lines, scribble or grayscale structure is extracted from the source automatically and guides the output, optionally with reference images for the subject or style, with native stereo audio generated in the same pass. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Video
Per video · quoted before submission
jev

minimax h3 · image to video LoRA

Open-weights MiniMax H3 image-to-video on WaveSpeed infrastructure: animate a first-frame image (optionally with a last frame) into a coherent 480p/540p/768p/1080p video with native stereo audio, 5-15 second durations, and affordable per-second pricing, with custom LoRA support.

Video
Per video · quoted before submission

Choose a model. Keep one video endpoint.

Pin a variant or let Auto compare compatible tasks within your key’s model pool and reservation limit.

Video API tutorial

Catalog prices refresh hourly. This public view may lag the latest sync by up to five minutes. Capabilities are provider-declared; availability can change.