Kling AI · Text to video
Kling 3.0
Kling 3.0 focuses on coherent action, stable subjects and cinematic pacing in short audiovisual scenes. It is useful for realistic B-roll, character moments and product stories where motion should remain understandable throughout the shot. Give clear action and camera directions, and use image guidance when a starting composition matters; this is especially helpful when comparing several ways to stage the same subject.
Generation mode
Text to video
Credit cost
42–1005 credits
Observed generation time
313 seconds
Release date
Feb 1, 2026
Current credit pricing
| Duration | Configuration | Credits |
|---|---|---|
| 3 seconds | 4K | 201 |
| 3 seconds | 4K_audio | 201 |
| 3 seconds | pro | 54 |
| 3 seconds | pro_audio | 81 |
| 3 seconds | std | 42 |
| 3 seconds | std_audio | 60 |
| 4 seconds | 4K | 268 |
| 4 seconds | 4K_audio | 268 |
| 4 seconds | pro | 72 |
| 4 seconds | pro_audio | 108 |
| 4 seconds | std | 56 |
| 4 seconds | std_audio | 80 |
| 5 seconds | 4K | 335 |
| 5 seconds | 4K_audio | 335 |
| 5 seconds | pro | 90 |
| 5 seconds | pro_audio | 135 |
| 5 seconds | std | 70 |
| 5 seconds | std_audio | 100 |
| 6 seconds | 4K | 402 |
| 6 seconds | 4K_audio | 402 |
| 6 seconds | pro | 108 |
| 6 seconds | pro_audio | 162 |
| 6 seconds | std | 84 |
| 6 seconds | std_audio | 120 |
| 7 seconds | 4K | 469 |
| 7 seconds | 4K_audio | 469 |
| 7 seconds | pro | 126 |
| 7 seconds | pro_audio | 189 |
| 7 seconds | std | 98 |
| 7 seconds | std_audio | 140 |
| 8 seconds | 4K | 536 |
| 8 seconds | 4K_audio | 536 |
| 8 seconds | pro | 144 |
| 8 seconds | pro_audio | 216 |
| 8 seconds | std | 112 |
| 8 seconds | std_audio | 160 |
| 9 seconds | 4K | 603 |
| 9 seconds | 4K_audio | 603 |
| 9 seconds | pro | 162 |
| 9 seconds | pro_audio | 243 |
| 9 seconds | std | 126 |
| 9 seconds | std_audio | 180 |
| 10 seconds | 4K | 670 |
| 10 seconds | 4K_audio | 670 |
| 10 seconds | pro | 180 |
| 10 seconds | pro_audio | 270 |
| 10 seconds | std | 140 |
| 10 seconds | std_audio | 200 |
| 11 seconds | 4K | 737 |
| 11 seconds | 4K_audio | 737 |
| 11 seconds | pro | 198 |
| 11 seconds | pro_audio | 297 |
| 11 seconds | std | 154 |
| 11 seconds | std_audio | 220 |
| 12 seconds | 4K | 804 |
| 12 seconds | 4K_audio | 804 |
| 12 seconds | pro | 216 |
| 12 seconds | pro_audio | 324 |
| 12 seconds | std | 168 |
| 12 seconds | std_audio | 240 |
| 13 seconds | 4K | 871 |
| 13 seconds | 4K_audio | 871 |
| 13 seconds | pro | 234 |
| 13 seconds | pro_audio | 351 |
| 13 seconds | std | 182 |
| 13 seconds | std_audio | 260 |
| 14 seconds | 4K | 938 |
| 14 seconds | 4K_audio | 938 |
| 14 seconds | pro | 252 |
| 14 seconds | pro_audio | 378 |
| 14 seconds | std | 196 |
| 14 seconds | std_audio | 280 |
| 15 seconds | 4K | 1,005 |
| 15 seconds | 4K_audio | 1,005 |
| 15 seconds | pro | 270 |
| 15 seconds | pro_audio | 405 |
| 15 seconds | std | 210 |
| 15 seconds | std_audio | 300 |
Availability and credit rows come from Flowctory's active production catalog. Observed time is shown only after at least five completed generations and is not a controlled benchmark. Model availability, limits, and costs can change.
Use model