跳转到内容
Alpha
  • 模型
  • 排行榜
  • Ori
联系销售

页脚

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

产品

  • 聊天
  • 排行榜
  • 基准测试
  • 应用
  • 发现
  • 模型
  • Ori
  • 合集
  • 提供商
  • 工具
  • 定价
  • Business
  • Enterprise
  • 实验室

公司

  • 关于
  • 博客
  • 客户
  • 招聘
    招聘
  • 隐私
  • 服务条款
  • 信任中心
  • 支持
  • 兼容 OR
  • 数据
  • 品牌

开发者

  • 文档
  • API 参考
  • 开发者平台
  • 状态
  • AI 站点地图

连接

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
krea 的网站图标

Krea: K3 Edit

krea/k3-edit

基准测试比较

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.

The default fast mode completes most edits in under ten seconds, which suits interactive editing tools and workflows that generate many variations of the same source image.

模态
价格
50% 优惠
from US$0.015/image
上下文
66K
发布时间
2026年10月15日
基准测试比较
试验场基准测试提供商定价性能正常运行时间应用活动常见问题探索

Example outputs summary for Krea: K3 Edit

  • Image to Image: Change the neon sign to a bright electric blue neon, and let its cool glow tint the facade and the reflections on the pavement below, while keeping the interior's warm lamp lighting unchanged so the windows still glow cozy and golden. Add gentle falling snow: a light dusting on the awning ledge, the potted plants, the bicycle seat, and the sidewalk, with fine snowflakes visible in the air against the dusk sky. Keep the composition and everything else exactly the same. The sign must still read exactly 'OpenRouter'. — 使用 Krea: K3 Edit 生成
  • Image to Image 2: Change the neon sign to a bright electric blue neon, and let its cool glow tint the facade and the reflections on the pavement below, while keeping the interior's warm lamp lighting unchanged so the windows still glow cozy and golden. Add gentle falling snow: a light dusting on the awning ledge, the potted plants, the bicycle seat, and the sidewalk, with fine snowflakes visible in the air against the dusk sky. Keep the composition and everything else exactly the same. The sign must still read exactly 'OpenRouter'. — 使用 Krea: K3 Edit 生成

试验场

基准测试

标准化评测得分，以及此模型针对共用基准测试提示词的实际输出。百分比越高越好，每项排名显示此模型在该来源所评测的模型中的位置。

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. (在此提示词中并列第 第 1 名，共 55 名)
  • 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. (在此提示词中并列第 第 23 名，共 55 名)
  • 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. (在此提示词中并列第 第 31 名，共 55 名)
  • 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. (在此提示词中并列第 第 1 名，共 55 名)
  • 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. (在此提示词中并列第 第 18 名，共 55 名)

提供商

此模型由一家提供商托管。OpenRouter 将每个请求直接转发给该提供商，无需做出路由决策。

定价

客户为此模型实际支付的平均价格，与提供商公布的价格并列展示。由于缓存和折扣，实际支付的价格往往远低于标价。

性能

吞吐量是模型生成内容的速度（每秒 token 数，越高越好）。延迟是完整的往返时间（越低越好）。TTFT 是首个 token 的响应时间，即您看到内容出现前需要等待的时间（越低越好）。

正常运行时间

正常运行时间是指过去 3 天中至少有一家提供商响应请求的时间百分比。可用性是指成功提供推理服务的时间百分比。OpenRouter 会持续监控，并在某家提供商返回错误时使用次优提供商。

应用

向此模型发送最多流量的公开应用。这能很好地反映实际生产工作负载的情况，也能提示此模型最适合哪些用例。

活动

此模型的 token 用量和请求流量随时间的变化。

API

可直接用于调用此模型的代码。OpenRouter 的 API 与 OpenAI 兼容——大多数 SDK 只需替换基础 URL 即可使用。切换模型时，唯一需要更改的是下方的模型标识符。

目前无法通过 EU 区域内路由使用。 区域内路由文档

探索更多模型

具备视觉能力的 AI 模型：用于图像理解的多模态大语言模型集合图像生成模型集合图像模型排行榜排名
端到端延迟
50% off
US$0.02US$0.01US$0.06US$0.0313.88s
100.00%
端到端延迟
13.88秒

P50，最佳提供商

正常运行时间（3 天）模型可访问。请求已路由至提供商。
100.00%
可用性（3 天）模型通过任意提供商返回了推理结果。错误和空响应均计为失败。
99.94%

过去 3 天的可用性

最近 72 小时
可用性 99.94%
3 天前2 天前昨天现在

过去 24 小时的可用性

OpenRouter Availability
99.92%

当上游提供商发生错误时，如果您的请求筛选条件允许，我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据： 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。

1.
https://github.com/comfyanonymous/ComfyUI 的网站图标
ComfyUI OpenRouter Extension
新增
2.29Mtoken
2.
https://stagespace.ai/ 的网站图标
Heisenberg Improve Prompt
新增
805Ktoken
3.
https://frame.studio/ 的网站图标
FRAME Studio
新增
796Ktoken
4.
https://github.com/claude-code-skills 的网站图标
external-llm-skill
新增
327Ktoken
5.
https://hunervan.com/ 的网站图标
Hunervan
新增
291Ktoken

常见问题

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.

K3 Edit 的费用为 Image Output 的价格为 从 US$0.015/image（1K）到 US$0.03/image（2K）、Image Input 的价格为 从 US$0.01/image（1K）到 US$0.035/image（2K）和High thinking mode 的价格为 US$0.01/generation。

K3 Edit 以 1K和2K 分辨率渲染和支持 1:1, 4:3, 3:2, 16:9, 4:5, 2:3 及另外 1 个 宽高比.

K3 Edit 接受 文本和图像 作为输入，并返回 图像。每个图像编辑请求最多可附加 8 张参考图像。

Krea 2 Large、Krea 2 Medium和Krea 2 Medium Turbo 是 Krea 的其他 图像 模型。

K3 Edit 于 2026年10月15日 发布。

更多模型，来自 krea

K3 Edit

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.

The default fast mode completes most edits in under ten seconds, which suits interactive editing tools and workflows that generate many variations of the same source image.

图像from US$0.015/image
Krea 2 Large

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.

图像from US$0.06/image
Krea 2 Medium

Krea 2 Medium is Krea's balanced, cost-efficient image generation model and a practical starting point for a broad range of use cases. Its extensive post-training supports stable, consistent generations, with particular strengths in illustration, anime, painting, and other expressive artistic styles.

图像from US$0.03/image
Krea 2 Medium Turbo

Krea 2 Medium Turbo is a distilled, speed-focused variant of Krea 2 Medium from Krea. It is designed for rapid iteration and graphic design exploration where fast generation is the priority.

图像from US$0.015/image