TheRouter.aiTheRouter.ai
Back to Models

Wan 2.2 T2I Plus

wanwan/wan2.2-t2i-plus

Wan 2.2 text-to-image — premium tier, higher fidelity.

wan2.2-t2i-plus is the premium tier of Wan 2.2 text-to-image. Compared with the flash tier it produces higher-fidelity images, better detail rendering, and stronger prompt adherence — at $0.08 per image and a longer generation time.

Like the flash tier, generation is asynchronous via `/v1/jobs` with an `img_`-prefixed job ID. Use this tier for delivery-grade creative: hero imagery, marketing keyframes, product visuals, and anything that ends up in front of customers.

$0.08 per image
Premium tier of Wan 2.2 — twice the flash price for delivery-grade output.
Higher fidelity
Better detail, prompt adherence, and composition than the flash tier — at the cost of longer generation time.
Async via /v1/jobs
Submit → poll → fetch URL. Job IDs prefixed with `img_`. Same flow as wan2.2-t2i-flash.
Dual-region routing
Selector picks bailian-cn or bailian-sg per request based on cost.
When to use
Delivery-grade creative: hero imagery, marketing keyframes, product shots, illustrations for publication, and anything that ships to end users.
When not to use
Bulk exploration, thumbnails, throwaway iteration — use wan2.2-t2i-flash at half the price and shorter latency.
Pricing: $0.08 per generated image. Billed per successful image. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request. Expect longer wall-clock time per job than the flash tier.
Context Length
--
Max Output
--
Image Price
$0.096/ image
Per image Price
$0.096/ image

Modalities

text→image

Pricing Breakdown

TypeRate
Image$0.096 / image
Per image$0.096 / image

Supported Parameters

promptsizenseed

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

Recommended: use the async API

Image generation typically takes 30–180s, beyond the edge sync timeout. The examples below use the ?async=true submit + poll pattern. Read the full async image generation & edit guide →

cURL
# 1) Submit job (returns 202 immediately with a polling URL).
# Image generation takes 30-180s — always use the async path in production.
JOB=$(curl -s -X POST "https://api.therouter.ai/v1/images/generations?async=true"   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "wan/wan2.2-t2i-plus",
    "prompt": "A cinematic product render with soft studio lighting"
  }' | python3 -c "import sys,json;print(json.load(sys.stdin)['id'])")
echo "submitted: $JOB"

# 2) Poll until terminal (succeeded / failed / cancelled / expired).
while :; do
  R=$(curl -s "https://api.therouter.ai/v1/jobs/$JOB"     -H "Authorization: Bearer $THE_ROUTER_API_KEY")
  S=$(echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['status'])")
  echo "status: $S"
  case "$S" in
    succeeded) echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['unsigned_urls'][0])"; break ;;
    failed|cancelled|expired) echo "$R"; exit 1 ;;
  esac
  sleep 5
done
Customer Support