Kling 4.0kling-4.ai Docs
Kling 4.0kling-4.ai Docs
Homepage

Getting Started

Overview

API Reference

X (Twitter)

Models

Currently supported Kling model identifiers and the boundary for future model availability.

Available now

Model stringStatusNotes
kling-v2-6DefaultThe current production Kling model on our pipeline. Used when model is omitted.
kling-v3-omniAvailableThe Omni workflow exposes model-specific reference, storyboard, resolution and audio options.

kling-v2-6 supports everything documented in Generate a Video: std/pro modes, 5s/10s durations, three aspect ratios, native audio (pro), negative prompts, and up to two reference images (end-frame control in pro).

Kling 4.0 at launch

Kling 4.0 is not integrated on this platform. We have not published a supported model identifier or a migration contract for it. See the availability tracker and official Kling announcements; do not submit speculative model IDs. Any future integration will require verified provider support and documented settings before access is advertised.

Requests with a model string the API doesn't recognize fail with 400 INVALID_INPUT, so you can deploy the new string the moment we announce availability and not before.

Which mode should you use?

  • std — cheaper and faster; text-to-video and single-reference work. Good for iteration: find your prompt in std, then re-render the keeper in pro.
  • pro — higher render quality, plus the pro-only features: native audio and two-image end-frame control.

For prompt technique — shot lists, camera language, film-stock grading — see the multi-shot prompt guide.

Table of Contents

Available now
Kling 4.0 at launch
Which mode should you use?