Kling: Video v3.0 Standard API
Kling 3.0 Standard is the entry-level tier of the Kling 3.0 family, generating 720p video with native audio from text or image prompts.
Kling 3.0 Standard is a multimodal generative model from Kling that produces video and audio in a single pass. Built on the Omni One architecture with 3D Spacetime Joint Attention and Chain-of-Thought reasoning, it accepts text or image inputs and outputs clips from 3 to 15 seconds long. It supports landscape, portrait, and square aspect ratios and can create multi-shot sequences of up to 6 shots per request, each with its own prompt and duration, while maintaining scene consistency across cuts. Audio—including dialogue, sound effects, and ambient sound—is generated natively alongside the video, eliminating a separate audio post-production step.
The model is designed for high-volume experimentation and rapid iteration. It is particularly suited for social media content for platforms such as Instagram, TikTok, and YouTube Shorts, e-commerce product videos, and short narrative sequences like mini commercials and story-driven posts. Physics-aware motion modeling—covering gravity, balance, deformation, collision, and inertia—helps avoid floating objects, broken limbs, and unnatural motion artifacts. Strong prompt adherence ensures high-fidelity interpretation of text and visual prompts, and semantic consistency is maintained across generations.
As the entry-level tier of the Kling 3.0 family, Standard renders video at 720p resolution. This is lower than the Pro tier at 1080p and the 4K tier at the largest size. Standard is positioned as the most cost-effective option among the three Kling 3.0 tiers. Kling 3.0 is described as the first unified multimodal model generating video, audio, and images within a single architecture. The model is available through platforms including Runway and fal, with API access offered through Runway Dev using the same endpoints, fields, and durations across all tiers, differing only in output size and price.
Updated:
MODEL ID
kling-v3.0-std- Output
- video
Highlights
- 720p video output
- Native audio generation
- 3 to 15 second clips
- Up to 6 shots per request
- Physics-aware motion
- Entry-level tier
Providers
Compare API prices across providers. Select a provider to view all charges and conditions.
| Uptime | |
|---|---|
Historical observations are not a live health check. Missing data does not mean an outage.
Video specifications
- Aspect ratios
- 16:9 / 9:16 / 1:1
- Audio · Output
- Yes
- Resolutions
- 720p
API reference
Model-specific protocol details are not published. Check the API reference for integration requirements.
API reference →Supported parameters
- prompt
- duration
- resolution
- aspect_ratio
- generate_audio
- size
- frame_images
- input_references
- user
- session_id
- trace
Frequently asked questions
What is Kling: Video v3.0 Standard?
Kling 3.0 Standard is a multimodal generative model from Kling that produces video and audio in a single pass. Built on the Omni One architecture with 3D Spacetime Joint Attention and Chain-of-Thought reasoning, it accepts text or image inputs and outputs clips from 3 to 15 seconds long. It supports landscape, portrait, and square aspect ratios and can create multi-shot sequences of up to 6 shots per request, each with its own prompt and duration, while maintaining scene consistency across cuts. Audio—including dialogue, sound effects, and ambient sound—is generated natively alongside the video, eliminating a separate audio post-production step. The model is designed for high-volume experimentation and rapid iteration. It is particularly suited for social media content for platforms such as Instagram, TikTok, and YouTube Shorts, e-commerce product videos, and short narrative sequences like mini commercials and story-driven posts. Physics-aware motion modeling—covering gravity, balance, deformation, collision, and inertia—helps avoid floating objects, broken limbs, and unnatural motion artifacts. Strong prompt adherence ensures high-fidelity interpretation of text and visual prompts, and semantic consistency is maintained across generations. As the entry-level tier of the Kling 3.0 family, Standard renders video at 720p resolution. This is lower than the Pro tier at 1080p and the 4K tier at the largest size. Standard is positioned as the most cost-effective option among the three Kling 3.0 tiers. Kling 3.0 is described as the first unified multimodal model generating video, audio, and images within a single architecture. The model is available through platforms including Runway and fal, with API access offered through Runway Dev using the same endpoints, fields, and durations across all tiers, differing only in output size and price.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices. Billed based on the actual generation cost. See your bill for the final amount.
What inputs does Kling 3.0 Standard accept?
It accepts text prompts or a first frame image with an optional last frame.
What video duration can it generate?
It produces clips from 3 to 15 seconds in duration.
Does it generate audio?
Yes, it natively generates dialogue, sound effects, and ambient sound in the same pass as video.
What is the output resolution?
It renders video at 720p resolution, which is lower than the Pro tier at 1080p and the 4K tier at the largest size.
How does it differ from other Kling 3.0 tiers?
Standard is the entry-level and most cost-effective tier, offering 720p output; Pro offers 1080p and 4K offers the largest size.