Agent Completion: a 15 s MiniMax H3 clip plus voiceover, cap 1.50
A 15-second MiniMax H3 clip at 768p ($1.125) plus a 750-character voiceover ($0.035625) comes to $1.160625, so a cap of 1.5 is enough. Table and body.
A 15-second MiniMax H3 clip at 768p ($1.125) plus a 750-character voiceover ($0.035625) comes to $1.160625 on Sume, so an Agent Completion needs a generation_spend_cap_usd of at least 1.17, and 1.5 leaves room. MiniMax H3 is $0.075 per second at 768p, and TTS is $0.0475 per 1,000 characters.
Line items
Both prices are linear, so the sum is exact.
| Item | Rate | Quantity | Total |
|---|---|---|---|
| MiniMax H3 768p | $0.075 per second | 15 s | $1.125 |
| TTS | $0.0475 per 1,000 characters | 750 characters | $0.035625 |
| Sum | $1.160625 |
Request
Pass the voiceover text as input data so it is not treated as instructions.
{
"instruction": "Make one 15 second MiniMax H3 clip at 768p of a mug, then narrate input.script over it.",
"input": { "script": "..." },
"generation_spend_cap_usd": 1.5
}Limits and gotchas
Joining the voice to the clip is not a separate priced line in this table, so confirm the final bill from the run's usage.
usage.generation_spend_cap_usd_microsechoes your cap on the receipt.next_actionstayspoll_statusuntil the run ends.- Cancel with
POST /v1/agent-runs/{id}/cancelif the instruction was wrong.
Sources
Related posts
More in Agents
- Agent Completion attachments: 16 full-size images fit the 500 MB cap
An Agent Completion takes up to 30 images, each up to 30 MB, in a set up to 500 MB. At full size only 16 fit; for 30 images the average must be under 16.7 MB.
- Agent Completion cap for ten Nano Banana 2.1 images at 2K: $1.50
Ten 2K Nano Banana 2.1 images cost $1.50 on Sume. Size generation_spend_cap_usd at $2 for headroom; 4K needs the whole $2.00. Table and curl.
- Agent Completion cap for three Wan 3.0 720p clips: $3.75 at 10 s
Three 10-second Wan 3.0 clips cost $1.875 at 480p, $3.75 at 720p and $7.50 at 1080p. How to pick generation_spend_cap_usd for each.
- Agent Completions rejects assistant turns: how to carry chat history
Sume Agent Completions return 400 on any assistant message in messages[] and start a fresh thread each time. Here is what that means for multi-turn history.
Written by Sume