Create Prediction

Endpoint

POST https://api.eachlabs.ai/v1/prediction

Request Body

Field	Type	Required	Description
`model`	string	Yes	Model slug (e.g., `flux-1-1-pro`)
`version`	string	Yes	Model version (e.g., `1.0.0`)
`input`	object	Yes	Input parameters (varies by model)
`fallback_selector`	string	No	Slug of an enabled, saved fallback configuration for your organization and the primary model. Omit to run only the primary model.
`webhook_url`	string	No	URL to receive prediction result via webhook
`webhook_secret`	string	No	Secret used to sign webhook requests. When set, each delivery carries `X-Webhook-Signature` and `X-Webhook-Timestamp` — see Verifying Webhook Signatures

The input object accepts model-specific parameters. Some models also support:

Input Field	Type	Default	Description
`enable_safety_checker`	boolean	`true`	Set to `false` to disable NSFW filtering. Only works on supported models.

Using a configured model fallback

Saving or enabling a model fallback does not automatically apply it to prediction requests. Include fallback_selector in every request that should use it, at the top level alongside model and input, not inside input. Use the saved configuration’s slug, not the fallback model’s slug or ID. The configuration must be enabled and belong to the API key’s organization and the requested primary model. The selector accepts 1-50 lowercase letters and digits separated by single hyphens. For example, if you have saved an enabled configuration with the slug quality-recovery for flux-1-1-pro:

{
  "model": "flux-1-1-pro",
  "fallback_selector": "quality-recovery",
  "input": {
    "prompt": "A beautiful sunset over the ocean",
    "aspect_ratio": "16:9"
  }
}

Replace quality-recovery with your saved configuration’s slug. Keep model and input set for the primary model; the saved configuration supplies the fallback models and input mappings. If fallback_selector is omitted, only the primary model runs, even when a fallback configuration exists.

Code Examples

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "flux-1-1-pro",
    "version": "1.0.0",
    "input": {
      "prompt": "A beautiful sunset over the ocean with vibrant colors",
      "aspect_ratio": "16:9"
    },
    "webhook_url": "https://your-app.com/webhook",
    "webhook_secret": "your-secret-key"
  }'

import requests

response = requests.post(
    "https://api.eachlabs.ai/v1/prediction",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer YOUR_API_KEY"
    },
    json={
        "model": "flux-1-1-pro",
        "version": "1.0.0",
        "input": {
            "prompt": "A beautiful sunset over the ocean with vibrant colors",
            "aspect_ratio": "16:9"
        }
    }
)

data = response.json()
print(f"Prediction ID: {data['predictionID']}")

const response = await fetch("https://api.eachlabs.ai/v1/prediction", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY",
  },
  body: JSON.stringify({
    model: "flux-1-1-pro",
    version: "1.0.0",
    input: {
      prompt: "A beautiful sunset over the ocean with vibrant colors",
      aspect_ratio: "16:9",
    },
  }),
});

const { predictionID } = await response.json();
console.log(`Prediction ID: ${predictionID}`);

Response

{
  "status": "success",
  "message": "Prediction created successfully",
  "predictionID": "abc123-def456-ghi789"
}

Response Fields

Field	Type	Description
`status`	string	`"success"` if prediction was created
`message`	string	Human-readable status message
`predictionID`	string	Unique ID to track the prediction

Error Responses

Status	Body	Description
`400`	`{"error": "Invalid input for model"}`	Input doesn’t match model schema
`400`	`{"error": "model field is required"}`	Missing required field
`401`	`{"error": "Invalid or missing API key"}`	Authentication failure
`500`	`{"error": "Failed to create prediction"}`	Server error

What Happens Next

After creating a prediction, the model processes your input asynchronously. Here’s how you can get your results:

Poll: Use Get Prediction to check status
Webhook: Provide a webhook_url and get results delivered automatically when they’re ready

Every model has different input parameters. Use Get Model to grab the request_schema for any model and see exactly what it expects.

Overview

Models

Predictions

Billing

Content Safety

Webhooks

OpenAPI Reference

Endpoint

Request Body

Using a configured model fallback

Code Examples

Response

Response Fields

Error Responses

What Happens Next

​Endpoint

​Request Body

​Using a configured model fallback

​Code Examples

​Response

​Response Fields

​Error Responses

​What Happens Next

Endpoint

Request Body

Using a configured model fallback

Code Examples

Response

Response Fields

Error Responses

What Happens Next