Type
Spec
Rate
Standard 480P
per second
$0.07
Standard 720P
per second
$0.14
Standard 1080P
per second
$0.28
Prime 480P
per second
$0.136
Prime 720P
per second
$0.28
Prime 1080P
per second
$0.56
Wan 3.0 and Wan 2.7 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Alibaba Cloud Video GenerationWan 3.0 and Wan 2.7 are both Alibaba Cloud models in the Video Generation category, available through the EmpirioLabs API.
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Wan 3.0 | Wan 2.7 |
|---|---|---|
| prompt | string | string |
| model_tier | standard, prime Default: standard | - |
| mode | auto, t2v, i2v, r2v Default: auto | auto, t2v, i2v, videoedit, r2v Default: auto |
| resolution | 480p, 720p, 1080p Default: 1080p | 720p, 1080p Default: 1080p |
| duration | 2 to 30 Default: 5 | 2 to 15 Default: 5 |
| aspect_ratio | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4 Default: adaptive | 16:9, 9:16, 1:1, 4:3, 3:4 |
| image | string | string |
| video | string | string |
| seed | 0 to 2147483647 | number |
| audio | boolean Default: true | - |
| watermark | boolean Default: false | - |
| prompt_extend | boolean Default: true | boolean Default: true |
| link | string | - |
| file_url | string | - |
| negative_prompt | - | string |
| audio_setting | - | auto, origin Default: auto |
Generation can take several minutes on the standard tier; the prime tier is significantly faster end to end. Modes are auto-detected from attachments, or override with the mode parameter. The model_tier parameter picks standard or prime; each tier bills at its own per-second rate.
Generation can take 30+ minutes. Modes auto-detected from attachments, or override with the mode parameter.
Wan 3.0 runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to wan-3-0 or wan-2-7. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3-0",
"prompt": "Describe what you want Wan 3.0 to generate."
}'Wan 3.0 is the newer release (Aug 6, 2026); Wan 2.7 was released on Apr 26, 2026. Capabilities listed only for Wan 3.0: text to video, image to video, reference to video. Capabilities listed only for Wan 2.7: multi shot. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Wan 3.0 is the newer release (Aug 6, 2026); Wan 2.7 was released on Apr 26, 2026.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/videos/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.