Wan 3.0 API Pricing: How Alibaba and Ofox Charge for Video Generation

Wan 3.0 is priced by resolution on Ofox. At 1080p the current public rate is $0.21 per second; a 5-second text-to-video estimate is $1.05. Higher resolutions do not share the 480p starting rate. The figures below were checked on 16 September 2026.

Current Ofox rates by resolution

All amounts are USD per second. Wan rows show public list prices; the primary supplier quotes match them in this snapshot: alicloud for Wan 3.0, aliyun for Prime and Wan 2.7/2.6. These are dated quotes, not a promise that prices will remain unchanged.

Price check: 2026-09-16. Five-second amounts estimate t2v with no input video; v2v totals require the input-video duration.

Estimating a five-second clip

Examples assume text-to-video (t2v), 5 seconds of output and no input video. They are estimates from public rates, not measured invoices. For requests with video inputs, include applicable input-video seconds and use the matching input-mode rate. Do not reuse the text-only total for a reference-video job; check final charges against the completed task.

Comparing Alibaba Cloud and Ofox

Alibaba Cloud direct billing and Ofox are separate offers. Compare the same resolution, region, input mode, audio settings and currency, and verify any discount expiry before calculating savings. Earlier claims that Ofox used one flat rate and saved 70% or 58% were incorrect. We have removed the unverified current Alibaba promotional comparison; the linked Alibaba documentation remains useful for direct API setup.

Choosing a model after the price correction

At 1080p, Wan 3.0 is 40% more expensive per second than Wan 2.7/2.6 ($0.21 versus $0.15). At 720p it is about 27.9% more expensive ($0.11 versus $0.086). Choose the newer model for capabilities your workflow needs and validate output quality; upgrading is not automatically a cost saving. Prime costs about 23.8% more than standard at 1080p ($0.26 versus $0.21); the premium differs by resolution. Its catalog description positions it for speed, but does not supply a measured latency guarantee.

What Wan 3.0 Actually Takes as Input

Up to 10 reference images, 5 reference videos and 5 reference audio clips in one request, with the video and audio each capped at 15 seconds total. Those caps are from Alibaba’s Wan 3.0 API reference, which is also where the duration rules live: an integer in the range 2 to 30 seconds, or -1 for intelligent duration, and when you pass input video the input plus output duration together cannot exceed 30 seconds.

Two defaults are worth knowing before your first call:

• Audio is on. The reference sets audio output to true by default, so the returned file has sound. Ofox exposes generate_audio if you want silence.
• Aspect ratio is adaptive. The supported set is 16:9, 4:3, 1:1, 3:4 and 9:16, with adaptive as the default, so the model picks unless you pin it.

Ofox’s model object reports the same envelope: min_duration_seconds: 2, max_duration_seconds: 30, supports_audio: true, resolutions 480p/720p/1080p with default_resolution: 1080p, and modes t2v, i2v, v2v.

How to Call Wan 3.0

Video generation is asynchronous everywhere: create a task, then poll. Alibaba’s own flow is documented as “创建任务 -> 轮询获取”, create the task then poll for the result, with the task_id and the resulting video URL each valid for 24 hours and a default query rate of 20 RPS.

Through Ofox the model sits on /v1/videos:

curl -X POST https://api.ofox.run/v1/videos \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-3.0",
    "prompt": "A paper boat drifting down a rain gutter, close on the water line",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

That returns a task you poll for status. The parameters Ofox lists on this model are prompt, duration, resolution, aspect_ratio, size, generate_audio, seed, frame_images, input_references, callback_url and provider. Passing frame_images selects first-frame or first-and-last-frame mode, input_references selects reference-to-video, so the mode follows from what you send rather than from a separate model string. callback_url is the alternative to polling if you would rather be told than ask; the video API polling guide covers the wait-time behaviour either way.

If a request comes back rejected instead, the Wan 3.0 error reference has the literal response body for each failure, including the duration range, the allowed aspect ratios and the model-string mismatch between Alibaba’s wan3.0-video and the gateway’s alibaba/wan-3.0.

Calling Alibaba directly, the endpoints are regional:

https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis
https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis

Both need a Model Studio API key and a workspace ID in the hostname.

Source and billing boundaries

Prices were checked on 16 September 2026 against the public Ofox catalog and the linked model pages. Compare the same resolution, input mode and audio settings, and distinguish public list prices from provider-specific quotes. Estimates assume the stated output length and no input video unless explicitly indicated; video inputs can add billable seconds. These examples are not measured invoices, and final charges depend on the completed task and applicable provider rate. Recheck prices before budgeting production usage.

• https://api.ofox.run/v2/models/catalog?limit=500&include=provider_price
• https://ofox.run/models/alibaba/wan-3.0
• https://ofox.run/models/alibaba/wan-2.7
• https://help.aliyun.com/zh/model-studio/wan3-video-generation-api-reference