Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for krea

Krea: Krea 2 Large

krea/krea-2-large

Compare

Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character, making it particularly suited for photorealism, expressive artistic styles, motion blur, grain, and low-dynamic-range looks.

Modalities

Price

from $0.06/image

Context

66K

Released

Jul 20, 2026

Compare
PlaygroundProvidersPricingPerformanceUptimeAppsActivityFAQ

Playground

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

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.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

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.

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.

Activity

Token volume and request traffic to this model over time.

Quick Start

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.

About Krea: Krea 2 Large

OpenRouter makes Krea: Krea 2 Large available through a unified, OpenAI-compatible API using the model ID krea/krea-2-large. It is served by Krea.

Krea: Krea 2 Large accepts text and images and returns images. It has a 65,536-token context window.

On OpenRouter, Krea: Krea 2 Large costs $0.06/image for Image Output, $0.065/image for Image Output (style references) and $0.07/image for Image Output (moodboards). It was released on July 20, 2026.

More models from Krea

  • Krea 2 Medium
  • Krea 2 Medium Turbo

Frequently asked questions

Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character, making it particularly suited for photorealism, expressive artistic styles, motion blur, grain, and low-dynamic-range looks.

Krea 2 Large costs $0.06/image for Image Output, $0.065/image for Image Output (style references) and $0.07/image for Image Output (moodboards).

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

Krea 2 Large accepts text and images as input and returns images. Up to 1 reference image can be attached to one request for image editing.

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

Krea 2 Large was released on July 20, 2026.

$0.060.14s145 tps
--

Throughput

145tok/s

P50, best across providers

Latency

0.14s

P50, best provider

Uptime (3d)

100.00%

Availability (3d)

99.82%

Availability over the last 3 days

Last 72 hours
Availability 99.82%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.45%

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 customization options.

1.
Favicon for https://buy.jewproxy.tech/
buy.jewproxy.tech
new
1.84Mtokens
2.
Favicon for https://latremontaise.com/
La Tremontaise - Veille
new
1.39Mtokens
3.
Favicon for https://model-assets.openrouter.ai/apps/marinara-engine.png
Marinara Engine
new
611Ktokens
4.
Favicon for https://github.com/local/orcli
orcli character profiles
new
485Ktokens
5.
Favicon for https://pdf-generator-app.local/
PDF Generator App
new
414Ktokens