# Kling | v3 | Text to Image

Kling V3 is the latest Kling image model, delivering enhanced visual quality, consistency, and detail.

## API Information

- **Model Slug:** kling-v3-text-to-image
- **Branded URL:** https://www.eachlabs.ai/kling/kling-v3/kling-v3-text-to-image
- **Provider:** Kling
- **Category:** Text to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.028 per image (input.num_images, default 1)
- **Estimated Processing Time:** 25 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/kling-v3-text-to-image

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0280
- **Pricing Details:** $0.028 per image (input.num_images, default 1)

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.028 per image (input.num_images, default 1) |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt for image generation. Max 2500 characters. |
| negative_prompt | string | No | - | - | Negative text prompt. It is recommended to supplement negative prompt information through negative sentences directly within positive prompts. |
| elements | array | No | - | 0–10 | Optional: Elements (characters/objects) to include in the image for face control. Each element can have a frontal image and optionally reference images. |
| resolution | string | No | 1K | 1K,2K | Image generation resolution. 1K: standard, 2K: high-res |
| num_images | integer | No | 1 | 1–9 | Number of images to generate (1-9). |
| aspect_ratio | string | No | 16:9 | 16:9,9:16,1:1,4:3,3:4,3:2,2:3,21:9 | Aspect ratio of generated images. |
| output_format | string | No | png | jpeg,png,webp | The format of the generated image. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-v3-text-to-image",
  "input": {
    "prompt": "A vast frozen polar landscape at twilight. Endless ice sheets and cracked glaciers stretching to the horizon. A smooth mirror like frozen lake in the foreground reflecting the sky and towering ice cliffs perfectly. Soft wind blowing fine snow across the surface, creating delicate trails. Cold blue tones mixed with subtle pink and purple sunset colors in the clouds. Light mist drifting above the ice, faint aurora glow in the sky. Cinematic lighting, ultra detailed ice textures, natural reflections, calm and silent atmosphere, photorealistic, sharp focus, 8K, high dynamic range."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

Kling | v3 | Text to Image is a cutting-edge text-to-image model from the Kling family by Kuaishou, transforming detailed text prompts into high-fidelity visuals with exceptional realism and detail.

As part of the Kling V3 family released in early 2026, this model addresses the need for print-ready, ultra-high-definition images without upscaling, delivering native 4K output directly. Its primary differentiator lies in enhanced narration and batch optimization capabilities, enabling creators to generate series of cohesive images with superior detail preservation and stylistic consistency. Available through each::labs (eachlabs.ai), Kling | v3 | Text to Image empowers designers, marketers, and developers to produce professional-grade visuals efficiently via the Kling | v3 | Text to Image API. Whether for concept art, product mockups, or marketing assets, it excels in rendering complex scenes with accurate physics, textures, and cinematic quality, streamlining workflows on each::labs.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.