Skip to main content
POST
/
{ownerName}
/
{modelName}
Create Request
curl --request POST \
  --url https://queue.modelrunner.run/{ownerName}/{modelName} \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "two friends cooking together",
  "negative_prompt": "worst quality, low quality, deformed, extra fingers",
  "width": 1280,
  "height": 1024,
  "num_outputs": 1,
  "scheduler": "K_EULER",
  "num_inference_steps": 4,
  "guidance_scale": 0,
  "seed": 103,
  "disable_safety_checker": "false"
}
'
{
  "request_id": "<string>",
  "response_url": "<string>",
  "status_url": "<string>",
  "cancel_url": "<string>",
  "logs": "<string>",
  "metrics": {
    "inference_time": 123
  },
  "queue_position": 123
}

Authorizations

​
Authorization
string
header
required

Use the format: Key modelrunner_key

Path Parameters

​
ownerName
string
default:bytedance
required

Model owner or organization name.

​
modelName
string
default:sdxl-lightning-4step
required

Model alias on ModelRunner.

Body

application/json

Model-specific input. Validated against the model's PredictionRequest schema at runtime.

​
prompt
string
​
negative_prompt
string
​
width
number
​
height
number
​
num_outputs
number
​
scheduler
string
​
num_inference_steps
number
​
guidance_scale
number
​
seed
number
​
disable_safety_checker
enum<string>
Available options:
false

Response

Request created

​
status
enum<string>
required
Available options:
IN_QUEUE,
IN_PROGRESS,
COMPLETED,
FAILED,
CANCELLED
​
request_id
string
required
Required string length: 21
​
response_url
string<uri>
required
​
status_url
string<uri>
required
​
cancel_url
string<uri>
required
​
logs
string
​
metrics
object
​
queue_position
number