Models
Currently supported Kling model identifiers and the boundary for future model availability.
Available now
| Model string | Status | Notes |
|---|---|---|
kling-v2-6 | Default | The current production Kling model on our pipeline. Used when model is omitted. |
kling-v3 | Available in Create | Kling 3.0: 3–15 seconds, 720p/1080p/4K, native audio, first/end frames, Elements and up to six storyboard shots. |
kling-v3-omni | Available | The 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 on the website
Kling 4.0 is available in the website generator through APIMart as kling-v4: text, first-frame images and ordered keyframes, 3–30 seconds, 720p/1080p, stereo audio. Sign-in and paid-source credits for the full order are required (from 85 credits for 720p, 3 seconds). The website Studio also supports Omni image/video/audio references, editing and extension. Flash and 4K are not integrated. The legacy public POST /api/ai-video/jobs endpoint does not accept kling-v4; do not copy the supplier model ID into that endpoint.
Requests with a model string the API doesn't recognize fail with 400 INVALID_INPUT, so submit a new model string only after it is listed in this API documentation.
Which mode should you use for Kling 2.6?
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.