Kling 4.0

Kling AI

Kuaishou’s Kling 4.0, fully available on the Kling API since 28 October 2026. It generates 3- to 30-second videos in a single run from text, images or video at 720p or 1080p, in 21:9, 16:9, 1:1, 9:16 or adaptive aspect ratios, with native audio and up to 10 keyframes. Its Omni reference endpoint accepts up to 15 inputs in a task, including up to 10 reference images and 5 reference videos, and can reference voices directly. With no input video it costs $0.157 a second at 720p and $0.235 at 1080p; with input video it costs $0.094 and $0.141 a second of total duration, which counts input and output. Kling lists 10-bit 4K as coming soon.

Full Specifications

All specsBest valueCheapestHeavy workloadMax capabilityDifferences only

	Kling 4.0Kling AI $0.157 (720p) / $0.235 (1080p) per second with no input video; $0.094 / $0.141 per second of total duration with input video (Kling API)
Identity
Developer	Kling AI
Released	Oct 2026
Status	Current — API fully available since 28 October 2026
Licence	API only — no open weights published
Cost
Price per second	$0.157 (720p), $0.235 (1080p) with no input video; $0.094 (720p), $0.141 (1080p) with input video, charged on total duration — Kling API balance price
Capacity
Max duration	30 seconds (3 to 30)
Max resolution	1080p (720p, 1080p); Kling lists 10-bit 4K as coming soon, with no 4K price yet
Capability
Text-to-video	Yes — single or multi-shot
Image-to-video	Yes — first and last frame, multi-keyframes, single or multi-shot
Native audio	Yes — plus voice reference on the Omni endpoint
Camera controls	Up to 10 keyframes per clip
Access
API	Yes — Kling AI API (kling-4.0): text-to-video, image-to-video and Omni reference-to-video; requires the Flagship Resource Pack or a topped-up balance