Retrieve task
Last updated September 7, 2026
Read a qwen/qwen-image-3.0-pro task in the Amux shape, with usage and cost.
Look up a qwen/qwen-image-3.0-pro task by the ID you got when submitting. It always
answers 200 whether or not the task is done; the state is in status, and
polling only needs that field.
https://gateway.amux.ai/v1/tasks/{id}Authorization
headerAuthorizationstringRequiredBearer <your Amux key> Your Amux API key.
Request
idstringRequiredThe task ID returned when you submitted.
Response
200responseThe task as it stands. succeeded carries output.
404responseNo such task, or it does not belong to this workspace. Both answer the same way, so that probing IDs across workspaces reveals nothing.
Polling cadence
Measured at 35–70 seconds. Wait 20 seconds after submitting, then poll every 5–10 seconds.
Artifacts are under output.images
Artifacts are grouped by type and an image model's live under images. The
videos field is still present and always empty; it cannot be used to tell
what modality a task is.
All three token fields are always 0
This model is billed per image and produces no tokens. What it cost is in
cost.
Two ways to retrieve
| Endpoint | Shape | When |
|---|---|---|
GET /api/v1/tasks/{id} | DashScope-native | DashScope clients build this address themselves |
GET /v1/tasks/{id} | Amux | preferred for new integrations; carries usage and cost |
Both read the same task, not two stores. The DashScope shape has no fields for usage or cost, so those two only appear on the Amux endpoint.
Errors
Errors come back in OpenAI's shape. The type values and their retry semantics are in Errors and retries.
curl https://gateway.amux.ai/v1/tasks/{id} \
-H "Authorization: Bearer $AMUX_API_KEY"{
"id": "task_01M1CG35C16CJ790D00BV1RBVM",
"status": "queued",
"model": "qwen/qwen-image-3.0-pro",
"created_at": "2026-09-07T11:25:44Z",
"output": {
"images": [
{
"index": 0,
"url": "https://cdn.amux.ai/gen/20260907/task_01M1CG35C16CJ790D00BV1RBVM-0.png"
}
],
"videos": [
{}
]
},
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0
},
"cost": "0.043",
"error": {
"message": "<string>",
"code": "<string>"
}
}