That's NeuralModel catalog

krea

Krea: Krea 2 Large

krea/krea-2-large

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

According to its OpenRouter catalog entry, krea/krea-2-large (canonical ID krea/krea-2-large-20260720) is an image generation model from Krea that accepts text and image inputs and produces images. The catalog describes it as Krea's high-capability image model, more than twice the size of Krea 2 Medium, with lighter post-training said to give outputs a rawer, more textured character. It lists a 65,536-token context length. No independent model card was available in this source pack, and no benchmark results are listed.[1]

Strengths

  • Accepts both text and image inputs and generates image outputs, per the OpenRouter catalog entry.[1]
  • Catalog describes it as Krea's high-capability image model, more than twice the size of Krea 2 Medium.[1]
  • Lighter post-training is described as giving outputs a rawer, more textured, flexible character; catalog lists a 65,536-token context.[1]

Limitations

  • Evidence is limited to the OpenRouter catalog; no independent model card was available in this source pack, so claims reflect marketplace text only.[1]
  • No benchmark entries are listed in the catalog, so real-world quality and speed should be validated on your own workloads.[1]
  • Per the catalog, output is image-only; the source description is truncated and no supported parameters or reasoning flag are reported.[1]

Where to use it

  • Potentially suited to text-to-image work where a textured, less heavily post-processed look is wanted; validate on your own prompts first.[1]
  • Could fit image-guided editing or variation workflows, since the catalog lists image input support.[1]
  • May suit pipelines that send long or structured prompts, given the listed 65,536-token context; confirm behavior in testing.[1]

Sources

  1. [1] OpenRouter catalog · Krea: Krea 2 LargeSources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

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,...

Specifications

Model ID
krea/krea-2-large
Canonical ID
krea/krea-2-large-20260720
Creator
krea
Added to OpenRouter
20.07.2026
Context length
65,536
Modality
text+image->image
Input modalities
text, image
Output modalities
image
Token pricing
No per-token price in the source snapshot — see OpenRouter for the billing unit
Knowledge cutoff
—
Expiration date
—

Tasks and capabilities

A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.

TaskGradeSource-declared capability
General qualityNo measurement—
CodingNo measurement—
AgentsNo measurement—
WritingNo measurement—
ReasoningNo measurement—
Document analysisNo measurement—
VisionNo measurementinput: image
Image generationNo measurementoutput: image
AudioNo measurement—
VideoNo measurement—
EmbeddingsNo measurement—

Evaluations

No evaluations are supplied for this model.

How grades work

Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.

  • S — S — top 10% of the cohort
  • A — A — next 20% of the cohort
  • B — B — next 30% of the cohort
  • C — C — below the B band

Providers

Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.

ProviderContext lengthPrice in /1MPrice out /1MLatency p50 (30m, s)Throughput p50 (30m, tok/s)Uptime (30m)
Krea65,536—————

Provider data retrieved: 13.11.2026

No published articles identify this model yet.