← Back to all models
Kling 3.0
Kling AI · kling-3
Kuaishou's multi-shot video model: up to five directed shots in one clip, with native audio and strong physical motion.
Starting price
usage-based
per second of video
Billing
Pay as you go
Service status
Active
Released
2026
About Kling 3.0
Kuaishou's multi-shot video model: up to five directed shots in one clip, with native audio and strong physical motion.
Kling 3.0 pricing
Billed by the seconds of video produced
usage-based
per second of video
This model is billed by the seconds of video produced and the resolution requested, and that rate is not published on this page.
Model id
Provider
Inputs
Outputs
Billing basis
Status
Released
Share model
Sample code and API for Kling 3.0
Point the base URL at CupAI and use your own API key; the rest of the request stays exactly as it is in any compatible client.
curl 'https://api.cupai.ir/v1/video-generate' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer $CUPAI_API_KEY' \
-d '{
"model": "kling-3",
"prompt": "a calm seaside at dawn"
}'Replace CUPAI_API_KEY with your own key.
Create an API key
Capabilities
Capabilities supported by this model's API.
text-to-audio
text-to-video
image-to-audio
image-to-video
Frequently asked questions about Kling 3.0
- How is usage of Kling 3.0 billed?
- This model is billed by the seconds of video it produces, not by tokens. The per-second rate depends on the resolution and the clip length, and the amount is deducted from your wallet.
- How do I connect to Kling 3.0?
- Point the base URL at CupAI, put your API key in the request header, and send the model id in the request body. Ready-made samples are on this page.
- How do payments work?
- Payments are in Toman and need no foreign credit card. Credit you buy can be spent on any available model.
Other models
How model pricing works
Every AI model strikes a different balance between speed, answer quality and cost. Flagship models suit complex reasoning, long-document analysis and precise code generation, while lighter models cost considerably less for summarising, classification and short answers. The list above shows each model's rate broken down by input token, output token and cache, so you can estimate the cost of your workload before you start.
A token is the smallest unit of text a model processes; roughly speaking a thousand tokens is about 750 English words. The cost of a request is the sum of its input and output tokens, so shortening your prompt and capping the response length reduces cost directly. Some models have a second price tier for very long inputs, which reprices the entire request once it crosses a stated threshold.