Kuaishou · Video

Hermes Agent x Kling

Kling is Kuaishou's flagship video model, supporting 4K, AI avatars, and multimodal audio. Through RunAPI, all Kling variants share unified API access and billing.

Public versions and endpoints

Model IDVersionEndpointsStarting priceCatalog
kling-3.0Native 4K, 15-sec max, multi-shot storyboarding
/api/v1/kling/motion_control
/api/v1/kling/text_to_video
$0.430Model detail
kling-ai-avatar-pro1080p enhanced lip-sync + facial micro-expressions
/api/v1/kling/ai_avatar
$0.160Model detail
kling-ai-avatar-standard720p basic lip-sync; ~half the cost of Pro
/api/v1/kling/ai_avatar
$0.080Model detail
kling-ai-avatar-v1-proV1 Pro avatar generation with audio-driven lip sync
/api/v1/kling/ai_avatar
$0.160Model detail
kling-o1All-purpose video generation guided by image and video references
/api/v1/kling/text_to_video
/api/v1/kling/image_to_video
$0.080Model detail
kling-v1-avatar-standardV1 Standard avatar generation for efficient talking heads
/api/v1/kling/ai_avatar
$0.080Model detail
kling-v2.1-master-image-to-videoPremium V2.1 image-to-video with stronger rendering
/api/v1/kling/image_to_video
$0.610Model detail
kling-v2.1-master-text-to-videoPremium V2.1 text-to-video with stronger rendering
/api/v1/kling/text_to_video
$0.610Model detail
kling-v2.1-proImage-to-video with optional final-frame control
/api/v1/kling/image_to_video
$0.100Model detail
kling-v2.1-standardLower-cost V2.1 image animation for quick drafts
/api/v1/kling/image_to_video
$0.050Model detail
kling-v2.5-turbo-image-to-video-pro1080p image-anchored; input image sets first frame
/api/v1/kling/extend_video
/api/v1/kling/image_to_video
$0.160Model detail
kling-v2.5-turbo-text-to-video-pro1080p, 10-sec max, 30 fps; fast text-to-video drafting
/api/v1/kling/text_to_video
/api/v1/kling/extend_video
$0.160Model detail
kling-v2.6Unified text- and image-to-video generation with synchronized native audio
/api/v1/kling/text_to_video
/api/v1/kling/image_to_video
/api/v1/kling/motion_control
$0.310Model detail
kling-v3-omniKling v3 Omni video generation with native 4K, synchronized audio, and flexible 3-15 second durations.
/api/v1/kling/text_to_video
/api/v1/kling/image_to_video
$0.910Model detail
kling-v3-turbo-image-to-video3-15s image-to-video clips from one first-frame image
/api/v1/kling/image_to_video
$0.180Model detail
kling-v3-turbo-text-to-video3-15s text-to-video clips at 720p or 1080p
/api/v1/kling/text_to_video
$0.180Model detail

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.

Verify

Select <model-id> to generate verification commands.

How it works

  1. 1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. 2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. 3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

FAQ

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.