Run Model Prediction Synchronously

curl --request POST \ --url https://api.eachlabs.ai/v1/prediction/run \ --header 'Content-Type: application/json' \ --header 'X-API-Key: <api-key>' \ --data ' { "model": "eachlabs-llm-router", "input": { "model": "openai/gpt-4o-mini", "messages": [ { "role": "user", "content": "Write a one sentence caption." } ] } } '

{ "status": "success", "message": "Prediction completed successfully", "predictionID": "abc123-def456-ghi789", "output": { "text": "A cinematic sunset over the ocean." }, "error": "" }

Authorizations

X-API-Key

string

header

required

API key for authentication

Body

application/json

model

string

required

Model slug or identifier

Example:

"flux-1-1-pro"

input

object

required

Input parameters for the prediction

Example:

{
  "prompt": "A beautiful sunset over the ocean with vibrant colors",
  "aspect_ratio": "16:9"
}

version

string

deprecated

Deprecated. This field is ignored. Kept for backwards compatibility.

Example:

"0.0.1"

webhook_url

string<uri>

Optional webhook URL to receive prediction result asynchronously

Example:

"https://your-app.com/webhook"

webhook_secret

string

Optional secret used to sign webhook requests

Example:

"your-secret-key"

Response

Prediction completed or failed synchronously

status

enum<string>

Final terminal status of the synchronous prediction

Available options:

success,

failed,

cancelled

Example:

"success"

message

string

Human-readable message

Example:

"Prediction completed successfully"

predictionID

string

Unique prediction identifier

Example:

"abc123-def456-ghi789"

output

Prediction output, when available

error

string

User-facing error message when the prediction failed

Example:

""