Video API catalog
Seedance, Veo, Wan, MiniMax, Grok Imagine and more — compare text-to-video, image-to-video and video editing versions with live per-second prices, then render through one async API.
Live catalog · prices sync from the platform every 5 minutes
Now showing
01/Catalog
Grouped by family, newest first. Every version links to its own page with parameters, pricing and sample code.
80 models
Alibaba3 versionsfrom$0.20/ secWan 3.0 Video Pro Spicy brings the Wan 3.0 contract - 2-30 second clips with native audio, first/last-frame control, and rich reference materials - to 1080P, 2K, and 4K output on a relaxed-moderation route for adult-orie…
wan3.0-pro-spicy-i2vImage to video$0.20/ secwan3.0-pro-spicy-r2vImage to videoVideo to video$0.20/ secwan3.0-pro-spicy-t2vText to video$0.20/ secAlibaba3 versionsfrom$0.06/ secWan 3.0 Video Spicy keeps the Wan 3.0 contract - 2-30 second clips with native audio, first/last-frame control, and rich reference materials - on a relaxed-moderation route for adult-oriented creative work.
wan3.0-spicy-i2vImage to video$0.06/ secwan3.0-spicy-r2vImage to videoVideo to video$0.06/ secwan3.0-spicy-t2vText to video$0.06/ sec
BytePlus2 versionsfrom$0.10/ secSeedance 2.5 X is an ultra-low-cost model version of Seedance 2.5 offered by the APIPod platform.
seedance-2.5-x-r2vImage to videoVideo to video$0.10/ secseedance-2.5-x-t2vText to video$0.10/ secBytePlus2 versionsfrom$0.70/ videoSeedance 2.0 X is an ultra-low-priced model version of Seedance 2.0 provided by the APIPod platform.
seedance-2.0-x-r2vImage to videoVideo to video$0.70/ videoseedance-2.0-x-t2vText to video$0.70/ videoBytePlus6 versionsfrom$0.059/ secSeedance 2.5 is ByteDance’s next-generation AI video model, built for up to 30-second video generation, advanced multimodal reference control, precise local editing, and more flexible, production-ready creative workflows…
seedance-2.5-draftImage to videoVideo to video$0.059/ secseedance-2.5-i2vImage to video$0.098/ secseedance-2.5-r2vImage to videoVideo to video$0.059/ secseedance-2.5-t2vText to video$0.098/ secseedance-2.5-editVideo to video$0.059/ secseedance-2.5-extendVideo to video$0.059/ sec
Google4 versionsfrom$0.036/ secGemini Omni Flash 1.1 is Google's lightweight preview model for fast, high-volume video generation and editing.
gemini-omni-flash-1.1-i2vImage to video$0.06/ secgemini-omni-flash-1.1-r2vImage to video$0.036/ secgemini-omni-flash-1.1-t2vText to video$0.06/ secgemini-omni-flash-1.1-extendVideo to video$0.80/ video
fal.ai2 versionsfrom$0.05/ secMiniMax H3 Max is the fal post‑trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics.
minimax-h3-max-i2vImage to video$0.05/ secminimax-h3-max-t2vText to video$0.05/ secAlibaba3 versionsfrom$0.06/ secWan3.0‑Video‑Prime is the high‑speed video generation model of Wanxiang 3.0. Its capabilities are aligned with the standard version of Wan3.0‑Video.
wan3.0-prime-i2vImage to video$0.06/ secwan3.0-prime-r2vImage to videoVideo to video$0.06/ secwan3.0-prime-t2vText to video$0.06/ secBytePlus3 versionsfrom$0.09/ secSeedance 2.5 Special‑Price Model, Full‑Power Version, comes with a material library, no face distortion, 100% real‑person pass rate, long‑term stability. Priced at roughly 60% of the official rate, supports 720P.
seedance-2.5-lite-t2vText to video$0.15/ secseedance-2.5-lite-i2vImage to video$0.15/ secseedance-2.5-lite-r2vImage to videoVideo to video$0.09/ secBytePlus3 versionsfrom$0.015/ secSeedance 2.0 Mini Budget Version Model, Full‑Power Version, comes with a material library, no face distortion, 100% real‑person pass rate, long‑term stability. Priced at roughly 60% of the official rate, supports 720P.
seedance-2.0-mini-lite-i2vImage to video$0.025/ secseedance-2.0-mini-lite-r2vImage to videoVideo to video$0.015/ secseedance-2.0-mini-lite-t2vText to video$0.025/ secBytePlus3 versionsfrom$0.042/ secSeedance 2.0 Fast Special‑Price Model, Full‑Power Version, comes with a material library, no face distortion, 100% real‑person pass rate, long‑term stability. Priced at roughly 60% of the official rate, supports 720P.
seedance-2.0-fast-lite-i2vImage to video$0.07/ secseedance-2.0-fast-lite-r2vImage to videoVideo to video$0.042/ secseedance-2.0-fast-lite-t2vText to video$0.07/ secBytePlus3 versionsfrom$0.051/ secSeedance 2.0 Special‑Price Model, Full‑Power Version, with material library, no face distortion, 100% real‑human pass rate, long‑term stability. Priced at roughly 60% of the official rate, 720P supported.
seedance-2.0-lite-i2vImage to video$0.085/ secseedance-2.0-lite-r2vImage to videoVideo to video$0.051/ secseedance-2.0-lite-t2vText to video$0.085/ secBytePlus3 versionsfrom$0.0096/ secThe Seedance 2.0 Mini model costs approximately half of the standard‑version model, runs twice as fast as the Fast variant, supports 480P/720P output, and is suitable for batch and large‑scale production.
seedance-2.0-mini-i2vImage to video$0.016/ secseedance-2.0-mini-r2vImage to videoVideo to video$0.0096/ secseedance-2.0-mini-t2vText to video$0.016/ secBytePlus3 versionsfrom$0.027/ secThe Seedance 2.0 Fast model shares the same task system as the standard version, supports 480P/720P output, delivers faster rendering at a lower unit price, and is suitable for draft iteration and high‑concurrency previe…
seedance-2.0-fast-i2vImage to video$0.045/ secseedance-2.0-fast-r2vImage to videoVideo to video$0.027/ secseedance-2.0-fast-t2vText to video$0.045/ secAlibaba3 versionsfrom$0.045/ secWAN 3.0 is an All‑in‑One reference‑based video generation model that uniformly supports multiple use cases including text‑to‑video, image‑to‑video (first‑frame / first‑and‑last‑frame), and reference‑based video generatio…
wan3.0-i2vImage to video$0.045/ secwan3.0-r2vImage to videoVideo to video$0.045/ secwan3.0-t2vText to video$0.045/ sec
MiniMax3 versionsfrom$0.09/ secMiniMax H3, opensource, unifies text, image, video, and audio for 2K video generation, multimodal referencing, native stereo sound, motion transfer, and precise editing.
minimax-h3-i2vImage to video$0.09/ secminimax-h3-r2vImage to videoVideo to video$0.09/ secminimax-h3-t2vText to video$0.09/ sec
xAI3 versionsfrom$0.018/ secGrok Imagine 1.5 is xAI's latest image-to-video model, which can convert a single static image into a smooth video with a cinematic feel.
grok-imagine-1.5-vipImage to video$0.055/ secgrok-imagine-1.5-fastImage to video$0.018/ secgrok-imagine-1.5-previewImage to video$0.02/ secGoogle4 versionsfrom$0.25/ videoGoogle Gemini Omni is a multimodal video generation and editing model. It can convert text, images and video references into coherent videos, and delivers stable scene consistency, world understanding capabilities and na…
gemini-omni-extendVideo to video$0.25/ videogemini-omni-i2vImage to video$0.25/ videogemini-omni-r2vImage to video$0.25/ videogemini-omni-t2vText to video$0.25/ videoGoogle7 versionsfrom$0.08/ videoGoogle DeepMind's upgraded AI video model offers realistic motion generation, extended video duration, multi-image reference control, and synchronized native audio output, supporting 1080p image quality.
veo3-1-fastText to videoImage to video$0.18/ videoveo3-1-fast-4kText to videoImage to video$0.50/ videoveo3-1-fast-refImage to video$0.18/ videoveo3-1-liteText to videoImage to video$0.08/ videoveo3-1-lite-4kText to videoImage to video$0.40/ videoveo3-1-qualityText to videoImage to video$0.80/ videoveo3-1-quality-4kText to videoImage to video$1.20/ videoAlibaba3 versionsfrom$0.10/ secThe Wan 2.7 video model enables one‑stop unified generation of text‑driven, image‑driven, and reference‑driven video content along with native synchronized audio.
wan2.7-i2vImage to video$0.10/ secwan2.7-t2vText to video$0.10/ secwan2.7-videoeditVideo to video$0.10/ secBytePlus3 versionsfrom$0.038/ secSeedance 2.0 is a new generation of AI video generation model launched by ByteDance, focusing on high-quality and long-duration video creation.
seedance-2.0-i2vImage to video$0.063/ secseedance-2.0-r2vImage to video$0.038/ secseedance-2.0-t2vText to video$0.063/ sec
KLING1 versionfrom$0.07/ secKling Motion Control is an AI video motion model launched by Kuaishou Kling.
Series overview: Kling Motion ControlxAI2 versionsfrom$0.018/ secGrok Imagine is an xAI's multimodal video model capable of generating images and short videos from text or images. It features fast generation speed, synchronized audio and video, deliver a more expressive visual style.
grok-imagine-i2vImage to video$0.018/ secgrok-imagine-t2vText to video$0.018/ secBytePlus7 versionsfrom$0.012/ secSeedance 1.0 is the latest video generation basic model launched by the ByteDance Doubao large model team.
seedance-1.0-lite-i2vImage to video$0.02/ secseedance-1.0-lite-i2v-refImage to video$0.02/ secseedance-1.0-lite-t2vText to video$0.02/ secseedance-1.0-pro-fast-i2vImage to video$0.012/ secseedance-1.0-pro-fast-t2vText to video$0.012/ secseedance-1.0-pro-i2vImage to video$0.03/ secseedance-1.0-pro-t2vText to video$0.03/ secBytePlus1 versionfrom$1.00/ videoMotion Control model can recreate any motion with you image, copy motion from any video and place your character into the same movement!
Series overview: Motion Control02/Field guide
Start from what you already have — a prompt, a frame or a clip — and price by the second.
Text-to-video builds a shot from a prompt. Image-to-video animates a first frame or follows reference images for consistent characters and products. Video-to-video edits, restyles or extends footage you already have.
Most video models bill per second of output, multiplied by the resolution tier; a few charge a flat price per clip. A ten-second 1080p shot costs more than five seconds at 720p — budget by duration × resolution.
Lite, fast, mini and draft versions are built for iteration. Explore prompts and camera moves there, then send the winning take to the pro tier for the final render.
Video renders take from seconds to minutes. Each request returns a task_id instantly; pass a callback_url to be notified on completion, and failed renders are refunded automatically.
03/FAQ
Send a request to /v1/videos/generations with a model ID, prompt and optional reference images or video. A task_id comes back immediately; poll /status/{task_id} or pass a callback_url, then download the video from the result URLs.
Each version shows its starting price, usually per second of output. Resolution tiers apply a multiplier on top. Costs are reserved when the task is submitted and refunded automatically if it fails.
It depends on the model, resolution and clip length — from under a minute for draft tiers to several minutes for long, high-resolution renders. Webhook callbacks let your app move on without waiting.
Filter the list by “Image to video”. Those versions accept a first frame or reference images and animate them while keeping subjects consistent.
A model can be served by several upstream channels. On a retryable error the request moves to the next healthy channel, and a channel that keeps failing is circuit-broken until it recovers, so outages don’t cascade into your product.
Sign up, grab a key, and call image, video and language models from one endpoint. Register now for free trial credits, no credit card required.