Wan 3.0 API

Wan 3.0 is a text to video, image to video and reference to video model by Alibaba Qwen, available on the Venice API as wan-3-0-text-to-video. Requests are anonymized, so the provider never sees your identity.

Wan 3.0 API pricing

Model ID	Variant	Privacy	Price
`wan-3-0-text-to-video`	Text to video	Anonymized	from $0.05 per second
`wan-3-0-image-to-video`	Image to video	Anonymized	from $0.05 per second
`wan-3-0-reference-to-video`	Reference to video	Anonymized	from $0.05 per second

Clip prices for wan-3-0-text-to-video, silent:

Duration	480p	720p	1080p
2s	$0.10	$0.21	$0.42
5s	$0.26	$0.52	$1.04
10s	$0.52	$1.04	$2.08
15s	$0.78	$1.56	$3.12
20s	$1.04	$2.08	$4.16
25s	$1.30	$2.60	$5.20
30s	$1.56	$3.12	$6.24

Wan 3.0 specifications

Spec	Value
Provider	Alibaba Qwen
Released	Aug 1, 2026
Privacy	Anonymized
Modes	text to video, image to video and reference to video
Resolutions	1080p, 720p, 480p
Durations	2s, 5s, 10s, 15s, 20s, 25s, 30s
Aspect ratios	16:9, 9:16, 1:1, 4:3, 3:4
Audio	Optional

How to use the Wan 3.0 API

Send requests to POST https://api.venice.ai/api/v1/video/queue with "model": "wan-3-0-text-to-video" and your API key.

# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-3-0-text-to-video",
    "prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
    "duration": "5s",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "audio": true
  }'

# 2. Poll until the MP4 is ready
curl https://api.venice.ai/api/v1/video/retrieve \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "wan-3-0-text-to-video", "queue_id": "<queue_id>" }' --output video.mp4

Wan 3.0 API FAQ

How much does the Wan 3.0 API cost?

From

0.052 to

0.21 per second of video, depending on resolution, duration and audio. A 5-second 720p clip costs $0.52. Call POST /video/quote for the exact price before queueing. Prices are in USD and can be paid in DIEM at parity.

What is the Wan 3.0 model ID?

Use wan-3-0-text-to-video as the model parameter. Other variants: wan-3-0-image-to-video (Image to video), wan-3-0-reference-to-video (Reference to video).

Is the Wan 3.0 API private?

Wan 3.0 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

What resolutions and durations does Wan 3.0 support?

Resolutions: 1080p, 720p, 480p. Durations: 2s, 5s, 10s, 15s, 20s, 25s, 30s. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Audio: optional, with "audio": true.

Which endpoint does the Wan 3.0 API use?

Queue a job with POST /video/queue, then poll /video/retrieve for the result.

Related models

Wan 2.7 API: from $0.11 per second
Wan 2.6 API: from $0.11 per second
MiniMax H3 API: from $0.10 per second
Flux 3 API: from $0.19 per second
MiniMax H3 Enhanced API: from $0.10 per second
Seedance 2.5 API: from $0.17 per second

Explore

By modality