Skip to main content
NewSeedance 2.5 is live→
ModelRunner
kuaishou avatar

Kling 2.1 Master Text-to-Video API

kuaishou/kling-video/v2.1-master/text-to-video

Generate a short, cinematic video from a text prompt at the premium master tier, tuned for the highest motion quality and cinematic fidelity.

0.28 per second of output video
OpenAPI

Model Input

Input

Text description of the video to generate.

Length of the generated video in seconds.

The aspect ratio of the generated video frame.

Additional Settings

Customize your input with more control.

Describe content to avoid in the generated video.

Min: 0 - Max: 1

How strongly the video follows the prompt. Higher values increase prompt adherence; lower values allow more creative motion.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Loading
Generated in 165.899 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1

Kling 2.1 Master Text-to-Video API

Kling 2.1 Master Text-to-Video is a text-to-video AI model by kuaishou. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.28 per second of video.

POST https://queue.modelrunner.run/kuaishou/kling-video/v2.1-master/text-to-video

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/kuaishou/kling-video/v2.1-master/text-to-video \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A lone lighthouse on a rugged coastal cliff at dusk, its beam sweeping across dark crashing waves as storm clouds rol…",
    "duration": "5",
    "cfg_scale": 0.5,
    "aspect_ratio": "16:9",
    "negative_prompt": "blur, distort, and low quality",
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/kuaishou/kling-video/v2.1-master/text-to-video/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/kuaishou/kling-video/v2.1-master/text-to-video/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("kuaishou/kling-video/v2.1-master/text-to-video", {
  input: {
    "prompt": "A lone lighthouse on a rugged coastal cliff at dusk, its beam sweeping across dark crashing waves as storm clouds rol…",
    "duration": "5",
    "cfg_scale": 0.5,
    "aspect_ratio": "16:9",
    "negative_prompt": "blur, distort, and low quality"
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/kuaishou/kling-video/v2.1-master/text-to-video",
    headers=headers,
    json={
      "prompt": "A lone lighthouse on a rugged coastal cliff at dusk, its beam sweeping across dark crashing waves as storm clouds rol…",
      "duration": "5",
      "cfg_scale": 0.5,
      "aspect_ratio": "16:9",
      "negative_prompt": "blur, distort, and low quality"
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

Input parameters of Kling 2.1 Master Text-to-Video
NameTypeRequiredDescription
promptstringyesText description of the video to generate.
durationenumnoLength of the generated video in seconds. One of: 5, 10. Default: "5".
aspect_ratioenumnoThe aspect ratio of the generated video frame. One of: 16:9, 9:16, 1:1. Default: "16:9".
negative_promptstringnoDescribe content to avoid in the generated video. Default: "blur, distort, and low quality".
cfg_scalenumbernoHow strongly the video follows the prompt. Higher values increase prompt adherence; lower values allow more creative motion. Default: 0.5.

Machine-readable: OpenAPI schema · llms.txt

Use Kling 2.1 Master Text-to-Video from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Kling 2.1 Master Text-to-Video becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint kuaishou/kling-video/v2.1-master/text-to-video.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run kuaishou/kling-video/v2.1-master/text-to-video on ModelRunner to generate video”. MCP setup guide.

Model Details

Model Details

Kling 2.1 Master is the premium master tier of the Kling text-to-video family, turning a written prompt into a short, cinematic clip with the highest motion quality and cinematic fidelity in the lineup. It is tuned for lifelike, physically coherent movement and rich detail, so the action, subject, and scene you describe render with strong prompt adherence and a polished, film-grade look. Choose a 5-second or 10-second clip and a 16:9, 9:16, or 1:1 aspect ratio to match landscape, vertical, or square delivery.

## Best for - Hero and establishing shots where motion quality and cinematic fidelity matter more than speed or cost - Turning a single descriptive prompt into a polished, film-grade clip with lifelike movement - Cinematic landscape (16:9) b-roll with camera motion and atmospheric detail - Social-ready vertical (9:16) clips and square (1:1) loops from text alone when top-tier quality is the priority

## Choose another model when - You want faster or cheaper generations and can trade some fidelity — use the Kling turbo text-to-video tier - You want to animate an existing photo or starting frame rather than generate from text alone — use an image-to-video model - You need a single still image, not motion — use a text-to-image model - You need clips longer than 10 seconds or fine frame-by-frame timeline control — use a dedicated long-form video tool

## Tips - Describe the subject, the action, and the setting in one coherent sentence; concrete motion verbs ("slowly pans", "rushes forward") translate well to on-screen movement - Use `negative_prompt` to suppress recurring artifacts such as blur, warping, or low-quality texture - Raise `cfg_scale` toward 1 for tighter prompt adherence, lower it toward 0 for looser, more creative motion (default 0.5 is a balanced starting point) - Match `aspect_ratio` to where the clip will run — 9:16 for stories/reels, 16:9 for landscape, 1:1 for feed loops

To run via the ModelRunner JavaScript client: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("kuaishou/kling-video/v2.1-master/text-to-video", { input: { prompt: "A serene mountain lake reflecting clouds at golden hour, gentle ripples on the water", duration: "5", aspect_ratio: "16:9", }, }); ```