Kling 2.1 Master text-to-video and image-to-video model. Premium quality video generation from text or images powered by Runware.
Added May 29, 2025
Approx. Price
$1.57 per video
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
5
2 duration options
Duration
Default
5
Options (2)
5 seconds, 10 seconds
Length of the generated video in seconds
Negative Prompt
Default
N/A
What to avoid in the video
Size
Default
1920x1080
Options (3)
16:9 (Wide / Landscape) - 1080p, 1:1 (Square) - 1080p, 9:16 (Tall / Portrait) - 1080p
Video resolution and aspect ratio
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#40 / 78
ELO
1129.0
Appearances
2,833
95% CI
-9/9
Image to Video
#41 / 72
ELO
1201.0
Appearances
3,033
95% CI
-10/10
Release Date 2025-05 · Matched as Kling 2.1 Master
Artificial Analysis APIRelated video models
Compare Kling 2.1 Master with similar models from the same provider or model family.
Kling 2.1 Pro
kling-v21-proKling 2.1 Pro image-to-video model. Higher quality video generation from images with text prompts. Requires an input image.
Kling 2.1 Standard
kling-v21-standardKling 2.1 Standard image-to-video model. Creates high-quality videos from images with text prompts. Requires an input image.
Kling 2.0 Master
kling-video-v2Kling 2.0 Master text-to-video and image-to-video model. Blockbuster-quality scenes, lifelike characters, and smooth motion from text. Supports both text to video and image to video.
Kling 3.0 Turbo Pro
kling-v3-turbo-proKling 3.0 Turbo Pro generates high quality 1080p video from text or a first-frame image with stronger prompt consistency, stable motion, multi-shot storyboards, and 3-15 second durations.
Kling 3.0 Turbo Standard
kling-v3-turbo-standardKling 3.0 Turbo Standard generates fast, cost-efficient 720p video from text or a first-frame image. Supports stable motion, multi-shot storyboard prompts, and 3-15 second durations.
Kling O3 4K
kling-o3-4kNative 4K Kling O3 model for text-to-video, image-to-video, and reference-to-video generation. Supports start/end frame control, up to 7 reference images, and 3-15 second durations.