Webinar teaser clip: MiniMax H3 Max, 10 seconds at 768p for $1.00

A 10-second webinar teaser with stereo sound is a minimax-h3-max job at $1.00 for 768p on Sume ($0.62 at 480p, $2.00 at 1080p). H3 Max always renders stereo audio and takes 5 to 15 seconds (Video Router, read 2026-10-05).

What do I send?

Send the speaker headshot or the title slide as the first frame. Keep speech out of the prompt unless you want a spoken line; for sound direction see MiniMax H3 sound design prompts.

curl -X POST https://api.sume.com/v1/videos \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax-h3-max","prompt":"Subtle push-in on the speaker portrait, soft studio light, quiet ambient room tone","duration":10,"resolution":"768p","aspect_ratio":"16:9","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/speaker.jpg"},"frame_type":"first_frame"}]}'

How does it compare with H3?

minimax-h3 is cheaper at 768p; minimax-h3-max adds 1080p.

How do I poll and download the result?

A submit returns 202 with id, polling_url, status and model. Poll GET /v1/videos/{id} until status is completed (the other terminal values are failed and cancelled), then download from GET /v1/videos/{id}/content?index=0 with the same bearer key. Put the webinar date and registration link in a caption: generated video text is not reliable.

curl https://api.sume.com/v1/videos/JOB_ID -H "Authorization: Bearer $SUME_API_KEY"
curl -L "https://api.sume.com/v1/videos/JOB_ID/content?index=0" \
  -H "Authorization: Bearer $SUME_API_KEY" --output clip.mp4

Which one should I pick?

For a quick draft use minimax-h3 at 768p; for a final at 1080p use minimax-h3-max. The longer comparison is H3 or H3 Max.