Kuaishou: Kling Image

Kling Image generates still pictures from a text prompt. It can be used to establish the look of a scene, explore a character concept, or prepare visual material for a later motion project.

Compare models

kling-image

AvailableKuaishouImageAsync

Price: From $0.028
Released: Feb 4, 2026
Modalities: Image

About Kling Image

Kling Image is Kuaishou's text-to-image model on the Kling platform. It generates stills from a written prompt and runs as an asynchronous job. It works for settling the look of a scene, exploring a character concept, or preparing frames to animate later with a Kling video model. It takes text only and does not edit existing images.

Where it works well

Text-to-image is its single operation, so the interface stays simple.
Stills made with it sit naturally in a Kling pipeline, where they can seed image-to-video work.
Asynchronous jobs suit batches of concept variations.
Useful for fixing character and scene look before spending on video.

When to choose another model

It does not edit existing pictures; for that, choose an image-editing model.
Kling Image 3.0 and Kling Omni Image are later options in the same family if you want newer image generations.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-image",
  "model": "kling-image",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Text to image

Parameter	Values and limits	Default	Notes
`n`	Not provided	`1`	Defaults to one output image. The model-specific maximum is not declared in this public contract.
`prompt`	Not provided	Not provided	Not provided
`resolution`	Not provided	Not provided	Model-specific resolution values and the default are not yet verified for this public operation.
`response_format`	Not provided	Not provided	The public image response selector accepts url or b64_json. A URL-only supply rejects b64_json before upstream execution. Omit this field to keep the selected supply response representation; no uniform omitted-field default is declared here.
`size`	Not provided	Not provided	Model-specific size values and the default are not yet verified for this public operation.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Pricing

per image

Verified price: —
Official price: $0.028per image

	Official priceper image	Verified priceper image	Discount
Price	$0.028per image	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 6:29 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Kling Image in Console with a prompt ready to edit or send.

Help me create an image with kling-image using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Concept art
Generate several looks for a character or environment from short text briefs and pick one to develop.
Storyboard frames
Make key frames for a sequence, then animate the best ones with an image-to-video model.
Marketing visuals
Draft hero images for landing pages and social posts from a written creative brief.

Prompt examples

A lighthouse on a cliff at dawn, thin fog on the water, painterly style, wide composition.

Character sheet of a young courier with a green scarf, front and side view, flat colors.

Product mock-up of a matte black thermos on a wooden table by a window, soft morning light.

FAQ

What does Kling Image do?

It creates still images from text prompts. It runs as an asynchronous job, so you submit a prompt and collect the picture when it finishes.

Can it edit my photo?

No. To change an existing image, use an image-editing model; use this one to generate new pictures from text prompts. Pair it with an editing model if your workflow needs both.

How does it relate to Kling's video models?

They share a maker and platform. A common flow is to generate a still and then animate it with an image-to-video model such as Kling 3.0.

Is there a newer Kling image model?

Yes. Kling Image 3.0 and Kling Omni Image come from the same maker. Compare their outputs on your own prompts before choosing one, since each family member has a slightly different focus.

How much does Kling Image cost?

On TokenLab, Kling Image costs $0.028 per image. The pricing table above shows the full breakdown.

Which endpoint should Kling Image use?

Use https://api.tokenlab.sh/v1/images/generations for Kling Image. The request example below shows the matching code shape.

Which operations does Kling Image support?

Kling Image supports Text to image. Select an operation above to see its endpoint and request example.