Kling 4.0 Reference API Pricing: $0.171/s (720p) · Text to Video

What is Kling 4.0 Reference?

Kling 4.0 Reference builds a shot from your references: up to 10 images, up to 5 video clips (2 to 30 seconds each), up to 7 named subjects built from 2 to 4 photos each, and up to 3 voice samples, 15 references in all. Mention them in the prompt as @image_1, @video_1 or by the subject's name (@Hero says "..."). Without reference clips the model generates its own audio; give a subject a voice sample and it speaks in that voice. With reference clips you can keep their original sound. Priced per second at the resolution you pick: the provider's rate plus a flat 20% platform fee, shown before you spend. With reference clips the per-second rate is lower, and the bill counts the clips' length as well as the output's (at least twice the output), exactly as the provider bills it.

Key Features

Up to 10 reference images and 5 reference clips

Named subjects from 2-4 photos, with optional voice

Voice references for spoken lines

3 to 30 seconds, 720p or 1080p, up to 21:9

What are Kling 4.0 Reference's strengths?

Character consistency from photo subjects

Dialogue in a referenced voice

Mixing images and clips in one shot

What are Kling 4.0 Reference's limitations?

With reference clips, their length is billed too (at least 2x the output)

Video subjects are not supported yet (use reference clips)

What is Kling 4.0 Reference best for?

Recurring characters across shots Dialogue scenes Restyling a scene from reference clips

How much does Kling 4.0 Reference cost?

Metric

FairStack

Details

720p(default)

$0.171/s

Billed per second, 20% platform fee included.

1080p

$0.255/s

Billed per second, 20% platform fee included.

Billing note

With video input: $0.102/s (720p), $0.153/s (1080p), billed on the output length plus the input videos' length (counted as at least the output length).

Subscription

None

Pay per generation only

How does Kling 4.0 Reference perform across capabilities?

Estimated from the Kling 4.0 launch notes, not benchmark-verified (PRD-1229)

motion quality

89%

visual quality

88%

prompt adherence

84%

temporal coherence

88%

character consistency

90%

camera control

82%

How do I use the Kling 4.0 Reference API?

curl

curl -X POST https://api.fairstack.ai/v1/generations/video \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-4-0-r2v",
    "input": {
      "prompt": "Your prompt here"
    }
  }'

Python

import os
import requests

response = requests.post(
    "https://api.fairstack.ai/v1/generations/video",
    headers={
        "Authorization": f"Bearer {os.environ['FAIRSTACK_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
      "model": "kling-4-0-r2v",
      "input": {
        "prompt": "Your prompt here"
      }
    },
)

result = response.json()
print(result["data"])

Node.js

const response = await fetch("https://api.fairstack.ai/v1/generations/video", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.FAIRSTACK_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "kling-4-0-r2v",
    "input": {
      "prompt": "Your prompt here"
    }
  }),
});

const result = await response.json();
console.log(result.data);

What parameters does Kling 4.0 Reference support?

Parameter

Type

Default

Details

aspect_ratio

enum

16:9

Options: 16:9, 9:16, 1:1, 21:9

resolution

enum

720p

Options: 720p, 1080p

duration

integer

5

Range: 3–30

keep_original_sound

boolean

false

elements

array_of_objects (optional)

—

voices

array_of_objects (optional)

—

Frequently Asked Questions

How much does Kling 4.0 Reference cost?

Kling 4.0 Reference costs $0.171/s (720p) on FairStack as of 2026-11-10. This price includes FairStack's transparent 20% margin on infrastructure cost. No subscription or monthly fee — you pay per generation only. Minimum deposit is $1.

What is Kling 4.0 Reference and what is it best for?

Kling 4.0 Reference builds a shot from your references: up to 10 images, up to 5 video clips (2 to 30 seconds each), up to 7 named subjects built from 2 to 4 photos each, and up to 3 voice samples, 15 references in all. Mention them in the prompt as @image_1, @video_1 or by the subject's name (@Hero says "..."). Without reference clips the model generates its own audio; give a subject a voice sample and it speaks in that voice. With reference clips you can keep their original sound. Priced per second at the resolution you pick: the provider's rate plus a flat 20% platform fee, shown before you spend. With reference clips the per-second rate is lower, and the bill counts the clips' length as well as the output's (at least twice the output), exactly as the provider bills it. Kling 4.0 Reference is best for Recurring characters across shots, Dialogue scenes, Restyling a scene from reference clips. Available via FairStack's REST API with curl, Python, and Node.js SDKs.

Does Kling 4.0 Reference have an API?

Yes. Kling 4.0 Reference is available via FairStack's REST API at api.fairstack.ai. Send a POST request to /v1/generations/video with your API key, the model key, and an input object (input.prompt). Works with curl, Python requests, Node.js fetch, and any HTTP client. No SDK installation required.

How does Kling 4.0 Reference compare to other video models?

Kling 4.0 Reference excels at Recurring characters across shots, Dialogue scenes, Restyling a scene from reference clips. It is a text to video model priced at $0.171/s (720p) on FairStack. Key strengths: Character consistency from photo subjects, Dialogue in a referenced voice. Compare all video models at fairstack.ai/models.