krea: Krea 3

Krea 3 is Krea's image generation and editing model, in beta. It edits one or more reference images from a text instruction, or generates an image from the prompt alone. References are passed as HTTP…

cloudflareWorkersAI/krea/krea-3

Krea 3 is Krea's image generation and editing model, in beta. It edits one or more reference images from a text instruction, or generates an image from the prompt alone. References are passed as HTTP(S) URLs in image_urls (up to 8). Outputs go up to 2K, with optional thinking_mode, aspect_ratio, seed and regional_edit controls.

Specifications & capabilities

Input
image, text
Output
image
Capabilities
imageOutput, multimodal, visionInput

Published prices

1–4 / 4

krea/krea-3 ↗

$0.03

Inference provider
cloudflareWorkersAI
Platform
krea
Unit
catalog_quote
Currency
USD
Billing conditions
label
output_size_1k
Billing label
output_size_1k
Pricing via
Cloudflare AI Gateway

krea/krea-3 ↗

$0.06

Inference provider
cloudflareWorkersAI
Platform
krea
Unit
catalog_quote
Currency
USD
Billing conditions
label
output_size_2k
Billing label
output_size_2k
Pricing via
Cloudflare AI Gateway

krea/krea-3 ↗

$0.03

Inference provider
cloudflareWorkersAI
Platform
krea
Unit
image
Currency
USD
Billing conditions
Billing label
Per image
Pricing via
Cloudflare AI Gateway

krea/krea-3 ↗

$0.07

Inference provider
cloudflareWorkersAI
Platform
krea
Unit
input_image
Currency
USD
Billing conditions
Billing label
Per input image
Pricing via
Cloudflare AI Gateway

Provider specifications & access

1–1 / 1

Krea 3 ↗

source model id
krea/krea-3
hosting
third-party
platforms
  • krea
architecture
input_modalities
  • image
  • text
output_modalities
  • image
capabilities

    Original sources

    1–2 / 2

    GitHub · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace