Luma UNI-1

Max size

–

Input → output

text, image → image

Weights

–

Providers

1 provider · price, latency and uptime

ProviderPer imageLatency p50Uptime · hourly, 24hRetention

Krea AI

direct API

$0.04–$0.13124 s

n<100

may retain

Listed price: $0.04–$0.13 / image
Most per image: $0.13
Precision: –
Regions: default
Headquarters: –
Data retention: May retain prompts

Supported parameters

npromptwidthheightmodestyleoutput_formatweb_searchstyle_images

Uptime · last 3 days10-13 11:00 – 10-16 10:07 UTC

TueWedThuNow

By default the router tries our listings in routing order and fails over before the first byte — never mid-answer. Uptime is our own measurement; an hour stays grey until it has a sample. Open the row for the provider's specs and policies.

Quickstart

any SDK — only the base URL changes

curl --max-time 480 https://api.routerplus.com/v1/images/generations \
  -H "Authorization: Bearer $TM_API_KEY" -H "content-type: application/json" \
  -d '{"model":"krea/luma/uni-1","prompt":"a red dot"}'

# OpenAI SDK — only the base URL changes
import base64, os
from openai import OpenAI
client = OpenAI(base_url="https://api.routerplus.com/v1", api_key=os.environ["TM_API_KEY"], timeout=480.0, max_retries=0)
r = client.images.generate(model="krea/luma/uni-1", prompt="a red dot")
image_bytes = base64.b64decode(r.data[0].b64_json)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.routerplus.com/v1", apiKey: process.env.TM_API_KEY, timeout: 480000, maxRetries: 0 });
const r = await client.images.generate({ model: "krea/luma/uni-1", prompt: "a red dot" });
const imageBytes = Buffer.from(r.data[0].b64_json, "base64");

.qs pre[hidden] { display: block; border-top: 1px solid var(--code-line); } .qsb { display: none; } .qcode::before { content: attr(data-lang); display: block; color: var(--code-muted); font-size: 11px; margin-bottom: 6px; }

Pricing

billed at the cost Krea AI reports · at most $0.13 per image

output image	$0.04 / image · mode=standard, referenceImageCount=0
output image	$0.043 / image · mode=standard, referenceImageCount=1
output image	$0.046 / image · mode=standard, referenceImageCount=2
output image	$0.049 / image · mode=standard, referenceImageCount=3
output image	$0.052 / image · mode=standard, referenceImageCount=4
output image	$0.055 / image · mode=standard, referenceImageCount=5
output image	$0.058 / image · mode=standard, referenceImageCount=6
output image	$0.061 / image · mode=standard, referenceImageCount=7
output image	$0.064 / image · mode=standard, referenceImageCount=8
output image	$0.067 / image · mode=standard, referenceImageCount=9
output image	$0.10 / image · mode=max, referenceImageCount=0
output image	$0.10 / image · mode=max, referenceImageCount=1
output image	$0.11 / image · mode=max, referenceImageCount=2
output image	$0.11 / image · mode=max, referenceImageCount=3
output image	$0.11 / image · mode=max, referenceImageCount=4
output image	$0.12 / image · mode=max, referenceImageCount=5
output image	$0.12 / image · mode=max, referenceImageCount=6
output image	$0.12 / image · mode=max, referenceImageCount=7
output image	$0.12 / image · mode=max, referenceImageCount=8
output image	$0.13 / image · mode=max, referenceImageCount=9

Every billed response carries usage.cost — recompute your bill from the wire.

Parameters

n — integer 1–1 (default 1)

prompt (required) — string

width — integer · 512–8192 · default 1024

height — integer · 512–8192 · default 1024

mode — standard · max (default standard) · default "standard"

style — auto · manga (default auto) · default "auto"

output_format — string or null

web_search — boolean · default false

style_images — array · up to 9 items · item fields: strength, url · Image prompts to use for the generation

Values outside these are refused with a 400 that names the field.

Uptime

10-13 11:00 – 10-16 10:07 UTC

Last 3 days–last 24h · TTFB p50 123,897 ms · uptime n<100

TueWedThuNow

An hour counts at the best provider's uptime: a request goes to another provider when one fails. Grey hours have no sample yet.