Kling is Kuaishou's video model family — Kling 2.1 Pro and Kling 3.0 — known for strong physical realism and motion in both text-to-video and image-to-video. The Kling API generates short clips programmatically. This guide explains the family, its pricing model, and how to run text-to-video on Kunavo today.
model field.Kling API pricing
Kuaishou bills Kling in credits rather than a public per-second dollar rate, so third-party reseller prices vary a lot and aren't directly comparable. Kunavo publishes a transparent per-video rate for its live model instead of a credit abstraction — which is why the honest recommendation today is Veo 3:
| Model | Pricing basis | On Kunavo |
|---|---|---|
| Kling 2.1 Pro / 3.0 | Kuaishou credits (no public USD/sec) | Roadmap — not enabled |
| Veo 3 (Google) | Per video, transparent USD | Live, from $0.16 / 8s 720p |
Text-to-video on Kunavo today
Kunavo exposes video generation through one OpenAI-style endpoint, POST /v1/video/generations. The live model is Veo 3, which produces cinematic clips with native audio. The request shape is identical to what a Kling call would be — only the model string differs:
import requests
# Live text-to-video on the same OpenAI-style endpoint. Swap the model
# string to Kling once it's enabled — the request shape is identical.
resp = requests.post(
"https://api.kunavo.com/v1/video/generations",
headers={"Authorization": f"Bearer {API_KEY}"},
json={
"model": "veo-3", # live today; Kling on the roadmap
"prompt": "a slow push-in on a neon-lit alley in the rain, cinematic",
"duration": 5,
"aspect_ratio": "16:9",
},
timeout=600,
)
print(resp.json()["data"][0]["url"])The Kling 3.0 API
Searches for the Kling 3.0 API refer to Kuaishou's latest generation — longer clips and improved motion fidelity over 2.1 Pro. Kling 3.0 is the exact model reserved in Kunavo's catalog (as kling-3-0, $0.14/second), and it goes live once the upstream standard text-to-video path stabilizes. The request shape shown above already matches it.
The live alternatives: Veo 3, Seedance 2, Wan 2.7
Google Veo 3 is the strongest generally available text-to-video model and live on Kunavo, with native audio and transparent per-video pricing (Lite from $0.16, Fast from $0.32, Quality from $1.92 per 8s 720p clip). For Kling's signature physical realism, Seedance 2 (live, from $0.093/second) is the closest match on motion coherence, and Wan 2.7 (live, $0.096/second) is the budget cinematic pick. For the whole model landscape see the text-to-video API guide, and for image-to-video and the async task lifecycle the video docs.
FAQ
What is the Kling API?
Kuaishou's text-to-video / image-to-video model family (Kling 2.1 Pro, Kling 3.0), known for physical realism, billed in credits.
Can I use Kling on Kunavo today?
Not yet — it's on the roadmap. The upstream path is unstable and there's no clean public USD price, so we don't list it. Use Veo 3 on the same endpoint today.
How much does the Kling API cost?
Kuaishou bills in credits, so there's no single public USD rate. The transparent, live option on Kunavo is Veo 3 from $0.16 per 8s 720p clip.
What's the best Kling alternative?
Veo 3 — the strongest live text-to-video model on Kunavo, with native audio and transparent per-video pricing.