everyais
← Model catalog

Krea 2 Raw Turbo

everyais/krea-2-raw-turbo

Krea 2 Turbo with lvladikov Krea2-Turbo-Distill-4step-LoRA (4 steps, BF16, 1024×1024). Community derivative served by BROZ; not an official Krea service. Model: https://huggingface.co/krea/Krea-2-Turbo — adapter: https://huggingface.co/lvladikov/Krea2-Turbo-Distill-4step-LoRA — use is subject to the Krea 2 license: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf . Local output safety filtering is enabled.

Community supplied

This model is served only by GPUs operated by a third-party supplier. Prompts are processed outside the everyais contracted cloud. Enable Allow community-supplied models in account settings to call it (off by default); organization API keys follow organization settings.

Available now

Method

The page starts with current public catalog metadata and reference costs; operational metrics are added only when measured samples are available.

Source and update

GET /models/catalog

Updated

Model type
Image
Released
Not published
Context window
-
Price unit
Per image
Maximum output
-
Model reference price (USD)
Per image
$0.002
Lowest-rate condition: allow community supply in account settings.

Capabilities

  • ✓ Image generation

Supported endpoints

  • /v1/images/generations

Usage and availability trend

Daily tokensInputOutput
0002026-09-232026-09-272026-09-23 · Requests 17 · Input 0 · Output 0 · Availability Insufficient sample2026-09-24 · Requests 3 · Input 0 · Output 0 · Availability Insufficient sample2026-09-25 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-09-26 · Requests 3 · Input 0 · Output 0 · Availability Insufficient sample2026-09-27 · Requests 2 · Input 0 · Output 0 · Availability Insufficient sample

Last 5 days · 2026-09-27 Input 0 · Output 0 tokens (partial day in progress).

Daily availability (success rate %)

Insufficient sample — not enough requests to publish a success rate.

Code example

Use the OpenAI SDK by changing only base_url.

from openai import OpenAI

client = OpenAI(
    api_key="everyais_...",
    base_url="https://api.everyais.com/v1",
)

image = client.images.generate(
    model="everyais/krea-2-raw-turbo",
    prompt="a quiet reading room at dawn",
    n=1,
)
print(image.data[0].url)
Full API docs

Compare models side by side

Compare capabilities, context windows, and reference prices to find a model for your use case. Your actual billed rate can differ by account.

Compare with another model
Contact support