Kling v3.0 Std Text-to-Video by KUAISHOU
kwaivgi/kling-v3.0-std/text-to-videoKling v3.0 Standard Text-to-Video model by Kuaishou. High-quality video generation from text prompts.
Set up the model and run your first generation.
Ctrl ⏎Examples
Runs published with this model. Load one into the playground and change whatever you like.
Wide-angle shot. A lone figure with a large backpack walking through a dust storm-swept post-apocalyptic desert ruin. Wind blowing their cloak. Slow camera dolly out to reveal the desolate environment. Grainy film look.
A young woman with long curly brown hair sits in a dark movie theater on a deep red velvet seat, holding a red paper cup in both hands. She gazes up at the screen with a soft, amused smile. Her expression shifts subtly — her eyes widen slightly with interest, then she lets out a gentle laugh, her shoulders rising briefly. Her curly hair sways ever so slightly as she tilts her head. The flickering light from the movie screen casts warm, shifting reflections across her face, alternating between soft highlights and shadow. She lifts the red cup slowly to take a sip, then lowers it back down. The dark cinema background with rows of empty red seats remains still and moody. Cinematic lighting, shallow depth of field, warm color grading. 4K, 24fps.
Providers
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | $0.071 /sec | — | — |
| fal.ai | — | — | — |
| OpenRouter | — | — | — |
| Replicate | — | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.
Questions
- $0.355 per generation on ElliSekiz — the provider's own price, billed 1:1 from a prepaid USD balance with no markup and no subscription. Failed generations are free.
- Atlas Cloud, fal.ai, OpenRouter, Replicate. Requests route to the cheapest available provider automatically, or you can pin one per request or per model.
- POST to https://ellisekiz.ai/api/v1/generations with "model": "kwaivgi/kling-v3.0-std/text-to-video" and your prompt, authenticated with an ElliSekiz API token. The API tab on this page has the full request for this model, including its own parameters.
- aspect_ratio, cfg_scale, duration, negative_prompt, sound, multi_shot, shot_type — each one is in the playground form on this page and in the API example.