Krea K3 Edit is an image-to-image editing model from Krea. It takes one to eight reference images plus a text prompt and returns a single edited image, following instructions that range from small local changes to complex multi-step edits while keeping the subjects and composition of the references intact. The output follows the shape of the input unless an aspect ratio is requested.

How much does K3 Edit cost?

K3 Edit costs from $0.03/image at 1K to $0.06/image at 2K for Image Output, from $0.02/image at 1K to $0.07/image at 2K for Image Input, and $0.02/generation for High thinking mode.

What image resolutions and aspect ratios does K3 Edit support?

K3 Edit renders at 1K and 2K and supports the 1:1, 4:3, 3:2, 16:9, 4:5, 2:3 and 1 more aspect ratios.

What inputs and outputs does K3 Edit support?

K3 Edit accepts text and images as input and returns images. Up to 8 reference images can be attached to one request for image editing.

Which providers serve K3 Edit?

K3 Edit is served by 1 provider on OpenRouter: Krea.

What other image models does Krea have?

Krea 2 Large, Krea 2 Medium, and Krea 2 Medium Turbo are other image models from Krea.

When was K3 Edit released?

K3 Edit was released on October 15, 2026.

K3 Edit - Image Generation API Pricing

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark outputs summary for Krea: K3 Edit

Minimal diff: From the reference photo, change only the sign text to "ROUTE 7 ESPRESSO - OPEN TILL 8". Keep the sign, wall, lighting and framing identical. (Tied 1st of 55 on this prompt)
Object removal: Remove only the second cup from the left in the reference photo. Leave the other four cups exactly as they are, in the same positions, and leave the shelf, towel, wall, plant and lighting untouched. (Tied 23rd of 55 on this prompt)
Person removal: In the reference photo, remove only the person in the yellow coat. Their shadow on the pavement and their reflection in the shop window must be removed as well. Reconstruct the pavement and the window glass behind them. The person in the red coat and the person in the green coat must stay completely unchanged, including their own shadows and their own reflections. Change nothing else in the frame. (Tied 31st of 55 on this prompt)
Product placement: Product photograph of the ceramic mug from the reference image, standing upright on a café table. Show the same side of the mug, from the same side-on eye-level angle as the reference, with the handle on the right. The shape, proportions, colours, moulded relief and every painted detail must match the reference exactly. Only the setting and lighting change: soft daylight in a café interior, shallow depth of field. (Tied 1st of 55 on this prompt)
Four references: Place the person from the portrait reference at the desk in the scene reference, wearing the rust orange canvas jacket from its reference and holding the navy blue travel mug from its reference in one hand. Keep the face, the jacket and the mug exactly as they appear in the references — same colours, same details, same proportions. Do not change the room. (Tied 18th of 55 on this prompt)

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

End-to-end latency


	$0.02	$0.06	7.41s	100.00%

Image input $0.02Image output $0.06
7.41s latency100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$269.60/M tokens

Output

$12.46/M tokens

K3 Edit — Price history

Price history

No effective price data for this selection

		$269.64	$12.46	0.0%	100.0%

Effective in $269.64Effective out $12.46
Token share
100.0%

Performance

Latency is how long it takes to generate and return the image (lower is better).

End-to-end latency

7.41s

P50, best provider

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.74%

Availability over the last 3 days

Last 72 hours

Availability 99.74%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.61%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

ComfyUI OpenRouter Extension

new

4.15Mtokens

2.

FRAME Studio

new

1.92Mtokens

3.

AVORA Image Fix

new

1.6Mtokens

4.

StageSpace

new

927Ktokens

5.

Road Rash remaining frames

new

889Ktokens

Rest of OpenRouter

710K

Top 5 Apps

0

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Krea: K3 Edit

Playground

Benchmarks

Providers