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.

18 variants from $0.05 / second Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use kling-3.0 when it matches the task: Native 4K, 15-sec max, multi-shot storyboarding.

You have access to RunAPI task tools for Kling.

Available Kling models:
- kling-3.0: Native 4K, 15-sec max, multi-shot storyboarding
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/motion_control
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution
- kling-ai-avatar-pro: 1080p enhanced lip-sync + facial micro-expressions
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-ai-avatar-standard: 720p basic lip-sync
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-ai-avatar-v1-pro: V1 Pro avatar generation with audio-driven lip sync
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-o1: All-purpose video generation guided by image and video references
  endpoints: /api/v1/kling/image_to_video, /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v1-avatar-standard: V1 Standard avatar generation for efficient talking heads
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-v2.1-master-image-to-video: Premium V2.1 image-to-video with stronger rendering
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.1-master-text-to-video: Premium V2.1 text-to-video with stronger rendering
  endpoints: /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v2.1-pro: Image-to-video with optional final-frame control
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.1-standard: Lower-cost V2.1 image animation for quick drafts
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.5-turbo-image-to-video-pro: 1080p image-anchored; input image sets first frame
  endpoints: /api/v1/kling/extend_video, /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.5-turbo-text-to-video-pro: 1080p, 10-sec max, 30 fps; fast text-to-video drafting
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/extend_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v2.6: Unified text- and image-to-video generation with synchronized native audio
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/image_to_video, /api/v1/kling/motion_control
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v3-omni: Kling v3 Omni video generation with native 4K, synchronized audio, and flexible 3-15 second durations.
  endpoints: /api/v1/kling/image_to_video, /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution
- kling-v3-omni-edit: Edit a source video with optional reference images
  endpoints: /api/v1/kling/edit_video
  request fields: model, prompt, source_video_url, reference_image_urls, duration_seconds, output_resolution, aspect_ratio, enable_sound
- kling-v3-omni-reference: Reference-image and source-video guided video creation
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/edit_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution, reference_image_urls
- kling-v3-turbo-image-to-video: 3-15s image-to-video clips from one first-frame image
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v3-turbo-text-to-video: 3-15s text-to-video clips at 720p or 1080p
  endpoints: /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution

Use the model ID and endpoint that match the user's request.
Example prompt: Create a 10-second video of a person walking through an autumn forest, leaves falling, cinematic camera pan.
/api/v1/kling/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/text_to_video and save the returned Task id.
GET /api/v1/kling/text_to_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/kling/motion_control: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/motion_control and save the returned Task id.
GET /api/v1/kling/motion_control/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/kling/ai_avatar: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/ai_avatar and save the returned Task id.
GET /api/v1/kling/ai_avatar/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/kling/image_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/image_to_video and save the returned Task id.
GET /api/v1/kling/image_to_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/kling/extend_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/extend_video and save the returned Task id.
GET /api/v1/kling/extend_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/kling/edit_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/edit_video and save the returned Task id.
GET /api/v1/kling/edit_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
kling-3.0
/api/v1/kling/text_to_video /api/v1/kling/motion_control
$0.43 / second Model detail
kling-ai-avatar-pro
/api/v1/kling/ai_avatar
$0.16 / second Model detail
kling-ai-avatar-standard
/api/v1/kling/ai_avatar
$0.08 / second Model detail
kling-ai-avatar-v1-pro
/api/v1/kling/ai_avatar
$0.16 / second Model detail
kling-o1
/api/v1/kling/image_to_video /api/v1/kling/text_to_video
$0.08 / second Model detail
kling-v1-avatar-standard
/api/v1/kling/ai_avatar
$0.08 / second Model detail
kling-v2.1-master-image-to-video
/api/v1/kling/image_to_video
$0.61 / second Model detail
kling-v2.1-master-text-to-video
/api/v1/kling/text_to_video
$0.61 / second Model detail
kling-v2.1-pro
/api/v1/kling/image_to_video
$0.10 / second Model detail
kling-v2.1-standard
/api/v1/kling/image_to_video
$0.05 / second Model detail
kling-v2.5-turbo-image-to-video-pro
/api/v1/kling/extend_video /api/v1/kling/image_to_video
$0.16 / second Model detail
kling-v2.5-turbo-text-to-video-pro
/api/v1/kling/text_to_video /api/v1/kling/extend_video
$0.16 / second Model detail
kling-v2.6
/api/v1/kling/text_to_video /api/v1/kling/image_to_video /api/v1/kling/motion_control
$0.29 / second Model detail
kling-v3-omni
/api/v1/kling/image_to_video /api/v1/kling/text_to_video
$0.91 / second Model detail
kling-v3-omni-edit
/api/v1/kling/edit_video
$0.91 / second Model detail
kling-v3-omni-reference
/api/v1/kling/text_to_video /api/v1/kling/edit_video
$0.91 / second Model detail
kling-v3-turbo-image-to-video
/api/v1/kling/image_to_video
$0.18 / second Model detail
kling-v3-turbo-text-to-video
/api/v1/kling/text_to_video
$0.18 / second Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

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

Get Started in 3 Steps

  1. Choose a model ID

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

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

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

What to Build with Hermes Agent + Kling

  • Longer narrative content

    Build scene-length footage by connecting establishing shots and character sequences with consistent visuals across clips.

  • Travel and nature content

    Generate travel B-roll and nature footage with realistic environments, including water, mist, and atmospheric lighting.

  • Product demo videos

    Animate a product image into a short video with camera movement and natural lighting transitions for e-commerce listings and social ads.

Why Use Kling Through RunAPI + Hermes Agent

  • 18 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

Hermes Agent + Kling Questions

Does Hermes Agent need a separate provider for Kling video?

No. If RunAPI is already configured in Hermes Agent for chat or images, the same provider and API key work for Kling video endpoints.

What happens if a Kling generation fails?

RunAPI bills only completed generations. If a task fails or times out, the reserved amount returns to your balance.

Can Hermes Agent combine Kling video with audio models?

Yes. Hermes Agent can generate a clip with Kling, then call a voice or music model through RunAPI to add narration or a soundtrack in the same workflow.

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.

Start using Kling with Hermes Agent

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us