Wan Text-to-Video

by Alibaba · Released , 4 days after Qwen MT Plus · Announcement · All Alibaba releases

Wan-t2v is Pruna's optimized text-to-video model that creates complete videos directly from text prompts, with no input image required. Part of the Wan family from Alibaba's Tongyi Lab, it generates 81 frames by default at 16 fps, producing roughly 5-second sequences at the chosen resolution and aspect ratio. The model supports 480p and 720p output across two aspect ratios: 16:9 landscape (832x480 or 1280x720 pixels) and 9:16 portrait (480x832 or 720x1280 pixels). Configuration includes frame counts from 81 to 121, frame rates from 5 to 30 fps, optional frame interpolation for 30 fps smoothness, custom LoRA weights, sample shifting, and seed control for fine-tuned generation. Wan-t2v suits pure text-to-video applications where creative freedom matters more than image consistency, including marketing videos, storyboarding, concept visualization, and content creation. It handles landscape and portrait formats natively, making it usable for multi-platform video distribution without reworking aspect ratios in post.

Sign up without a credit card · POST /v3/videos
Pricing
$0.10 / generation
Routes
1 US

Available routes

Wan Text-to-Video runs on 1 route through the Opper gateway.

ProviderRegionZero data retentionTrainingPrice
USNo$0.10 / generation

Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Live routes and prices as JSON: api.opper.ai/v3/models?q=pruna%2Fwan-t2v

Key info

Input
Output
Features
Pricing
$0.10 / generation
Billing
Per generation
Released
  • US residency available
  • Zero data retention with abuse monitoring
  • No training by default

Pricing

Usage-based pricing, billed per generation, not by token.

VariantPrice
Standard$0.10 / generation

Data handling per route

Each route hosting Wan Text-to-Video has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Pruna — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content
Transfer mechanism
SCCs

Get started

Call Wan Text-to-Video through the Opper gateway with one API key. Video models run on Opper's async video endpoint: POST /v3/videos answers 202 with a status URL, which you poll until the job is completed and then download the file from its url.

See the Opper video guide and the Opper multimodal skill.

Wan Text-to-Video is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

# 1. Submit the job: answers 202 with an id and a status_url
STATUS_URL=$(curl -s https://api.opper.ai/v3/videos \
-H "Authorization: Bearer $OPPER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "pruna/wan-t2v",
"prompt": "A paper boat drifting down a rain-soaked street at dusk",
"seconds": 5,
"resolution": "720p",
"aspect_ratio": "16:9"
}' | jq -r .status_url)
# 2. Poll the status_url (GET /v3/artifacts/{id}/status) until "status"
# is "completed" (or "failed")
curl "$STATUS_URL" -H "Authorization: Bearer $OPPER_API_KEY"
# 3. Download the clip from the "url" in the completed status
curl -o video.mp4 "<url>"

Use Wan Text-to-Video in your apps

Pick your tool, then choose Wan Text-to-Video to see how to run it through Opper.

Compare Wan Text-to-Video with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Alibaba

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation