kling/kling-v1-t2v

Docs
Schema

[Core Function] Kling V1 T2V is an older generation text-to-video model. [Strengths] Pioneered early realistic physics simulation in video generation. Maintained for backward compatibility. [Best For] Existing legacy integrations and workflows that strictly depend on this specific model version's quirks. [Limitations] Do NOT use this for new creations. It is a legacy model maintained for backward compatibility. [Routing] Only use if explicitly requested; otherwise use Kling V3 T2V.

$0.0320~$0.1120/sec
text-to-video

Input

Video description text, supports Chinese and English
Negative prompt describing undesired elements
Video aspect ratio
16:9
Prompt relevance, controls how closely the generated content matches the prompt (0.0-1.0). Only supported by V1 and V1.6.
Video duration in seconds
5
Generation mode: std (standard, faster) or pro (professional, higher quality but longer processing)
std

Result

No results yet

Run the model to preview the output here.

Next:

README

Parameters

Name Description Type Required Enums
prompt Video description text, supports Chinese and English string Yes -
negative_prompt Negative prompt describing undesired elements string No -
aspect_ratio Video aspect ratio string No 16:9, 9:16, 1:1
cfg_scale Prompt relevance, controls how closely the generated content matches the prompt (0.0-1.0). Only supported by V1 and V1.6. number No -
duration Video duration in seconds integer No 5, 10
mode Generation mode: std (standard, faster) or pro (professional, higher quality but longer processing) string No std, pro

Pricing

Unit: $/sec

Dimension Pricing
mode: pro / duration: 10 0.1120
mode: std / duration: 10 0.0320
mode: pro / duration: 5 0.1120
mode: std / duration: 5 0.0320