Retrieve task
Last updated September 7, 2026
Look up a minimax/minimax-h3 task in the unified shape, with usage and cost.
Look up a minimax/minimax-h3 task in the unified shape, with usage and cost.
https://gateway.amux.ai/v1/tasks/{id}Authorization
headerAuthorizationstringRequiredBearer <your Amux key> Your Amux API key.
Request
idstringRequiredThe Amux task ID returned at submit time.
Response
200responseAlways 200, finished or not -- the state is in status.
404responseNo such task in this workspace.
Always 200, finished or not
The state lives in status, so polling only has to read that one field.
status | Meaning | Charged? |
|---|---|---|
queued | Queued | — |
running | Generating | — |
succeeded | Complete; artifacts in output.videos | Charged on actual usage |
failed | Upstream refused or errored | Not charged, reservation released |
canceled | Canceled by you | Cancelling after submission is still charged |
expired | Never completed and no longer retrievable | Not charged, reservation released |
Usage and cost
usage.output_video_seconds is the duration the upstream reported, and cost
follows it. This model bills for input material: reference images per image and reference video by its input duration (at the output tier's rate); reference audio is free.
notes: what we did to your request
Present only when something was done. The most common one on this model is the ratio filled in for text-only generation:
set ratio=16:9: this model requires an explicit ratio for text-only generation
No key means it went upstream unchanged.
Artifact URLs
output.videos[].url points at our storage. Links are cleaned up periodically —
download anything you need to keep.
output.images is always an empty array but the field is always present — it is
kept for existing image clients, so it cannot be used to tell the modality.
curl https://gateway.amux.ai/v1/tasks/{id} \
-H "Authorization: Bearer $AMUX_API_KEY"{
"id": "task_01M1VD9E8WRYVBR7ES10SNQQQT",
"status": "queued",
"model": "minimax/minimax-h3",
"created_at": "<string>",
"output": {
"images": [
{}
],
"videos": [
{
"index": 0,
"url": "<string>"
}
]
},
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0,
"output_video_seconds": 0
},
"cost": "0.36",
"notes": [
"<string>"
],
"error": {
"message": "<string>",
"code": "<string>"
}
}