Create Async Job

Create an async job for long-running AI operations.

Model format: feature/subfeature/provider[/model]

Supported async features:

• audio/speech_to_text_async

Request body:

• model: Model string in format feature/subfeature/provider[/model]
• input: Feature-specific input parameters
• fallbacks: Optional list of fallback provider strings (max 3)
• webhook_receiver: Optional URL to receive job completion notification
• user_webhook_parameters: Optional custom parameters for webhook payload

Returns 202 Accepted with job info for polling.

POST /v3/universal-ai/async

Create Async Job

cURL

curl --request POST \
  --url https://api.edenai.run/v3/universal-ai/async \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {},
  "provider_params": {},
  "fallbacks": [
    "<string>"
  ],
  "show_original_response": false,
  "webhook_receiver": "<string>",
  "user_webhook_parameters": {}
}
'

202

{
  "cost": "<string>",
  "provider": "<string>",
  "feature": "<string>",
  "subfeature": "<string>",
  "public_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "output": "<unknown>",
  "error": {},
  "original_response": "<unknown>",
  "model": "<string>"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Universal AI async request body.

Extends UniversalAIBody with webhook parameters for async notifications.

model · string · required

Model in format: feature/subfeature/provider[/model]

Examples:

"text/ai_detection/openai/gpt-4"

"ocr/ocr/amazon"

"image/generation/google/imagen-3"

input · Input · object · required

Feature-specific input parameters. Required fields depend on the feature/subfeature specified in provider. Examples:

• text/ai_detection: {'text': 'content to analyze'}
• text/embeddings: {'texts': ['text1', 'text2']}
• ocr/ocr: {'file_id': 'abc123', 'language': 'en'}
• image/generation: {'text': 'prompt', 'resolution': '1024x1024'}
• translation/document_translation: {'file_id': 'abc123', 'target_language': 'fr'}

Examples:

{
  "text": "Analyze this text for AI detection"
}

{
  "dimensions": 512,
  "texts": ["text1", "text2"]
}

{ "file_id": "abc123", "language": "en" }

provider_params · Provider Params · object | null

Provider-specific parameters

fallbacks · string[]

Fallback providers to try if the primary provider fails, in order. Accepted formats:

• 'provider' or 'provider/model' (e.g. 'amazon', 'openai/gpt-4')
• full model id (e.g 'text/moderation/google', 'image/generation/minimax/image-01')

Maximum array length: 3

show_original_response · boolean | null · default: false

Include raw provider response in the output

webhook_receiver · string<uri> | null

Webhook URL to receive job completion notification

Required string length: 1 - 2083

user_webhook_parameters · User Webhook Parameters · object | null

Custom parameters to include in webhook payload

Response

202

application/json

Successful Response

Async response from universal-ai/async endpoint.

Inherits base fields and adds job-specific fields for tracking async operations. Used for both job creation (202 Accepted) and job detail (GET) responses.

status · enum<string> · required

Request status: success, fail, or processing (async only)

Available options: success, fail, processing

cost · string · required

Cost in credits for this request

Pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$

provider · string · required

Provider name that processed the request

feature · string · required

Feature category (e.g., text, ocr, image)

subfeature · string · required

Specific subfeature (e.g., ai_detection, sentiment)

public_id · string · required

Job ID for polling status

created_at · string<date-time> · required

Job creation timestamp

output · any | null

Normalized output from the provider

error · Error · object | null

Error details from the provider (only present when status is 'fail')

original_response · any | null

Raw response from the provider (if show_original_response=true)

model · string | null

Model name if specified in the request