Console

Qwen Image 3

Max size
–
Input → output
text, image → image
Weights
Open
Providers
1
01

Providers

1 provider · price, latency and uptime
ProviderPer imageLatency p50Uptime 24hRetention
1
Krea AI
$0.04–$0.075– – may retain
Listed price
$0.04–$0.075 / image
Most per image
$0.075
Precision
–
Regions
default
Headquarters
–
Data retention
May retain prompts
Supported parameters
npromptwidthheightseedstyle_images

By default the router tries our listings in routing order and fails over before the first byte — never mid-answer. Uptime is our own 24h measurement; a dash means too few requests to measure yet. Open the row for the provider's specs and policies.

02

Quickstart

any SDK — only the base URL changes
curl --max-time 480 https://dev-api.routerplus.com/v1/images/generations \
  -H "Authorization: Bearer $TM_API_KEY" -H "content-type: application/json" \
  -d '{"model":"krea/alibaba/qwen-image-3","prompt":"a red dot"}'
03

Pricing

billed at the cost Krea AI reports · at most $0.075 per image
output image$0.04 / image · resolutionTier=1k
output image$0.075 / image · resolutionTier=2k

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

04

Parameters

n — integer 1–1 (default 1)
prompt (required) — string
width — integer · 512–2048 · default 1024
height — integer · 512–2048 · default 1024
seed — number · default 1337
style_images — array · up to 3 items · item fields: strength, url · Image prompts to use for the generation

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