HeyGen Avatar IV on HiAPI costs $0.15 per second of output video. 720p and 1080p are the same price, so a 10-second talking-photo clip comes to $1.50.
HeyGen Avatar IV is live on HiAPI. Open the model page, upload a portrait, type a script, and the person in the photo starts talking.
How much does a HeyGen Avatar IV video cost?
| Video length | Price |
|---|---|
| 5 seconds | $0.75 |
| 8 seconds | $1.20 |
| 10 seconds | $1.50 |
| 15 seconds | $2.25 |
| 30 seconds | $4.50 |
| 60 seconds | $9.00 |
There is a single price tier, billed on the actual length of the video you get back. When you create a task, HiAPI holds an amount based on the estimated length; once the video is done, you are charged for the real seconds and the difference is settled automatically. Failed tasks are refunded in full.
On the model page, prices show in credits: 300 credits per second, with 2,000 credits = $1.
What a first test costs: $10 buys about 66 seconds of video, roughly six 10-second clips. That is enough to try one photo with several different scripts before you commit. Make your first video on the model page →
What decides how long the video is?
You never send a duration. With a script, length follows the words and the speaking pace of the voice. With your own audio, the video runs exactly as long as the recording. So estimating the price means estimating the read-aloud time of your script.
The landscape explainer below runs 9 seconds and cost $1.35. Lin keeps the sweater, hairstyle and room from the original photo, while her lips, blinks and small nods follow the voice:
Settings: 1080p, 16:9, voice Cute Chloe - Friendly. The script:
Hi, I'm Lin. With one photo and a short script, I can present your product or record a lesson, with natural lip-sync and expressions.
The script is filled in for you. Upload your photo and generate →
What will a month of videos cost?
Videos per month × seconds per video × $0.15:
| Use case | Videos per month | Total seconds | Monthly cost |
|---|---|---|---|
| 30-second product intros | 100 | 3,000 | $450 |
| 60-second course lessons | 20 | 1,200 | $180 |
| 10-second social clips | 300 | 3,000 | $450 |
A hundred 30-second videos and three hundred 10-second clips land on the same bill, because both add up to 3,000 seconds. Plan your budget in total seconds and split it however your publishing schedule needs.
Should you pick 720p or 1080p?
Pick 1080p. Both tiers cost the same, so the sharper one is free. The API defaults resolution to 720p, so set 1080p explicitly in your request.
Aspect ratio works the same way: 16:9, 9:16, 4:5, 5:4, 1:1 and auto are all billed per second, so choose whatever fits the placement.
How do you keep the bill down?
- Keep scripts tight. Cost tracks seconds and nothing else. Cut the warm-up line, lead with the point, and every sentence you trim comes off the bill.
- Test a new photo with a short line first. Run a few seconds of script to check the lip-sync and expression, then send the full script once you like the result. Front-facing, single-person photos with even light, an unobstructed face and a relaxed closed mouth work best.
- Match the aspect ratio to the photo. Use 9:16 for a vertical portrait, or auto to keep the photo's own ratio, so the frame needs no fill.
- Submit each task once. Poll with the returned
taskIdor receive the result viacallback.url. A repeated POST creates a new task and is billed again. - Download right away. Output links expire, so save the MP4 as soon as the task succeeds instead of paying to generate it twice.
Short vertical product clips are where tight scripts pay off. This earbuds review came out at 8 seconds, $1.20:
I've been using these new earbuds for a week. The noise canceling is super quiet, and the battery lasts all day. Follow me for more.
The script is filled in for you. Upload a vertical photo and generate → Set the aspect ratio to 9:16 and the resolution to 1080p.
Is HeyGen Avatar V the same price?
Yes, $0.15 per second for both. The difference is where the presenter comes from:
| Avatar IV | Avatar V | |
|---|---|---|
| Presenter | One photo you upload | 497 preset avatars |
| Resolution | 720p / 1080p | 720p / 1080p / 4k |
| Transparent background, caption file | — | Yes |
| Price | $0.15 / second | $0.15 / second |
If you have a photo and want that specific person on screen, use Avatar IV. If you can work with a preset presenter and want a transparent background, captions or 4K, use HeyGen Avatar V.
FAQ
Do 720p and 1080p cost the same? Yes. Both are $0.15 per second, so go with 1080p.
Am I charged for failed generations? No. The amount held for a failed task is refunded in full.
What if the final length differs from the estimate? It settles itself. You are charged for the actual seconds, and any gap from the held amount is refunded or topped up automatically.
How is audio-driven video billed? The same way, per second. The video matches your audio's length, and audio can run up to 600 seconds.
Make your first video now
We have loaded a business-update script for you. Upload a half-body office photo, set the aspect ratio to 16:9 and the resolution to 1080p, then hit Run:
Hi, I'm Daniel. Send me your quarterly numbers, and I'll walk your team through what changed and what to do next.
Open the model page with this script filled in → When we ran it, the video came out at 8 seconds and cost $1.20.
More on HeyGen Avatar IV
- HeyGen Avatar IV model page: generate from your photo and watch real outputs
- HeyGen Avatar IV API tutorial: from photo to talking video
- HeyGen Avatar IV API reference: every parameter and response field
- HeyGen Avatar V model page: 497 preset avatars with transparent backgrounds and 4K
- HiAPI pricing: every model in one place
