Sume Avatar Video quality default: what plus costs vs standard
Omit quality and Avatar Video runs on plus, not standard. On 20-second clips that is $1.22 more each, or $122 over 100 clips. The arithmetic and a safe default.
The quality field on Avatar Video takes standard, plus or max, and the API reference says plus is the default when you omit it. That matters for budgets: code written against a price you remember for standard bills at the plus rate until you set the field.
The gap is plain arithmetic. Standard bills $0.184 per second without a product image and plus bills $0.245, a difference of $0.061 per second.
What is the cost of forgetting the field?
Twenty seconds is a common length for a social avatar clip. At that length the default costs $1.22 more per clip without a product image and $1.28 more with one. Over a hundred clips the unplanned spend is $122 or $128.
| Case | Standard | Plus (default) | Extra per clip | Extra over 100 clips |
|---|---|---|---|---|
| No product image | $3.68 | $4.90 | $1.22 | $122.00 |
| With product image | $3.88 | $5.16 | $1.28 | $128.00 |
How do you avoid it?
Set quality explicitly in every request, and keep it in a shared constant rather than relying on the default. Read the amount from the response or the usage page after the first job to confirm the tier you intended.
If your tool wraps the API, check that it does not drop an unset field. A clear sign of a missed field is a charge of $4.90 on a 20-second no-product clip, which is the plus rate, instead of $3.68.
- Standard, no product, 20 s: $3.68
- Plus, no product, 20 s: $4.90
- Max, no product, 20 s: $11.00
When is plus the right choice anyway?
Plus is a sensible default if you have not compared tiers. This post does not claim a visible quality gap between tiers; run one script at both and decide. What it does say is that the choice should be made on purpose, because at volume it is the largest single lever on avatar spend, bigger than the product image surcharge or the clip length you trim by a second or two.
Sources
Related posts
More in Sume Avatar 1.0
- Azure photo avatar is 512x512; Sume avatar video is 720p
Azure's photo avatar renders head-only at 512x512 and 25 fps. Sume's avatar video offers 720p in five aspect ratios, from a prompt, traits or a photo.
- Azure avatar batch: 20-minute videos, 200 jobs, vs Sume
Azure's text to speech avatar batch API allows 20-minute outputs and 200 concurrent jobs per Speech resource. Sume avatar videos run 4-60 seconds per job.
- How to check a face swap result: audio, length and stills
Check a Sume face swap before publishing: confirm the audio stream, compare length with the source, and sample stills with video inspect. Free probe.
- Create an AI spokesperson avatar from a prompt or photo
Sume Avatar 1.0 creates a reusable avatar at a flat $0.95 from a text prompt, a photo, or props. How to make one before you generate talking videos.
Written by Sume