Wan 2.2
Alibaba's Wan 2.2 Plus — higher-quality text-to-video.
Alibaba$0.13 / secondtext-to-videoalibaba
Tier
Est. cost$0.65$1 ≈ 7 seconds of video.
Example output
$0.13/ second
$0.13 per second. $1 ≈ 7 seconds of video.
Pay only for successful generations. No idle, no minimums, no per-seat.
API
Wire it up.
Endpoint
POST https://api.tryinfer.com/v1/inference/wan2.2-plus/text-to-videorequest
curl https://api.tryinfer.com/v1/inference/wan2.2-plus/text-to-video \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A serene mountain lake at golden hour, cinematic lighting"
}
}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| seed | integer | — | — | — |
| prompt | string | Yes | — | — |
| resolution | string | — | 1080p | 480p1080p |
| aspect_ratio | string | — | 16:9 | 16:99:161:1 |
| duration_seconds | integer | — | 5 | — |
Authenticate with a bearer token. Get an API key →
Further reading
From the Infer content directory.
Best ofBest AI models for anime and stylized video in 2026Kling 3.0 Pro leads on documented anime/cinematic motion, Seedance 2.0 Pro adds audio in one pass, Wan 2.2 is the open-weights pick for style fine-tuning.Best ofBest open-source AI video and image models in 2026Wan 2.2 T2V-A14B leads open-source video on clean Apache 2.0 terms; SAM 3.1 leads segmentation; LTX-2 scores higher but its license is revenue-gated.GuidesFal vs Replicate vs Infer: which platform in 2026Fal wins on latency, Replicate on catalog depth, Infer on multimodal price. This is Infer's own blog comparing itself, so here's the honest breakdown.