Kling Video
Parameters below were verified against the live model directory on November 5, 2026. Check the model directory for current schema, availability, and prices.
Overview
Section titled “Overview”Kling V3 Omni is Kuaishou’s flagship general-purpose video generation model in the Kling (KeLing) series, unifying long-video generation, multimodal references (image/video/character), automatic multi-shot assembly, and optional audio generation into a single model interface. It supports three resolution tiers — Standard (720p), Pro (1080p), and 4K (2160p) — along with advanced capabilities such as multi-shot assembly, reference-video style transfer, and first-frame/end-frame specification.
The full model guide, live parameter schema, and playground for every model ID are available in the HiPix model directory.
Model IDs
Section titled “Model IDs”| Model ID | Mode | Notes |
|---|---|---|
kwaivgi/kling-v3-0/text-to-video | Text-to-Video | |
kwaivgi/kling-v3-omni | Text-to-Video, Image-to-Video, Video-to-Video, Audio-reference | |
kwaivgi/kling-video-o1 | Text-to-Video, Image-to-Video, Video-to-Video |
Parameters
Section titled “Parameters”Requests are submitted to POST /v1/videos (video) or POST /v1/images/generations / POST /v1/images/edits (image). Fields marked metadata.* travel inside the metadata object.
kwaivgi/kling-v3-0/text-to-video
Section titled “kwaivgi/kling-v3-0/text-to-video”| API field | Type | Required | Values / limit |
|---|---|---|---|
prompt | string | Yes | — |
metadata.mode | enum | Yes | std, pro; default std |
metadata.aspect_ratio | enum | Yes | 9:16, 16:9, 1:1, 3:4, 4:3; default 16:9 |
seconds | number | Yes | 4–15 (integer); default 5 |
metadata.sound | enum | Yes | on, off; default on |
metadata.watermark_info | boolean | No | true / false |
kwaivgi/kling-v3-omni
Section titled “kwaivgi/kling-v3-omni”| API field | Type | Required | Values / limit |
|---|---|---|---|
prompt | string | Yes | — |
metadata.video | array | No | up to 3; ≤200 MB each; videos |
metadata.image | array | No | up to 9; ≤30 MB each; images |
metadata.mode | enum | Yes | std, pro, 4k; default std |
metadata.aspect_ratio | enum | Yes | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9; default 9:16 |
seconds | number | Yes | 4–15 (integer); default 5 |
metadata.sound | enum | Yes | on, off; default on |
kwaivgi/kling-video-o1
Section titled “kwaivgi/kling-video-o1”| API field | Type | Required | Values / limit |
|---|---|---|---|
prompt | string | Yes | — |
metadata.video | array | No | up to 3; ≤200 MB each; videos |
metadata.image | array | No | up to 9; ≤30 MB each; images |
metadata.mode | enum | Yes | std, pro; default std |
metadata.aspect_ratio | enum | Yes | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9; default 9:16 |
seconds | number | Yes | 4–15 (integer); default 5 |
metadata.sound | enum | Yes | on, off; default on |
Example
Section titled “Example”A minimal request for kwaivgi/kling-v3-0/text-to-video:
curl -X POST https://api.apimart.cc/v1/videos \ -H "Authorization: Bearer $HIPIX_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "kwaivgi/kling-v3-0/text-to-video", "prompt": "A kitten running through a sunlit garden", "seconds": 5, "metadata": {"mode": "std", "aspect_ratio": "16:9", "sound": "on"}}'Poll the task with GET /v1/videos/{task_id} until status is completed or failed.
Limits, availability, and pricing
Section titled “Limits, availability, and pricing”- Submit only the input types listed for the exact model ID; unsupported inputs are rejected or removed on HiPix.
- See Submit a Video Task or the model directory for the full request contract, and Pricing & Billing for how charges are settled.
- Prices and availability are shown per model ID in the model directory.