Skip to main content
Kling V3 — text & image to video with first/last frame, multi-shot and element references. Standard, Pro and 4K quality.

Text → Video

Select it with "mode": "text_to_video", or leave mode out and the inputs decide. Required: prompt
Optional: aspect_ratio, duration_seconds, cfg_scale, negative_prompt, generate_audio, shot_type, elements
Resolution tiers: standard, pro, 4k (send as tier).

Image → Video

Select it with "mode": "image_to_video", or leave mode out and the inputs decide. Required: prompt, first_frame
Optional: last_frame, elements, duration_seconds, cfg_scale, negative_prompt, generate_audio, shot_type
Resolution tiers: standard, pro, 4k (send as tier).
Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/kling-v3-fal is always current.