Effortlessly handle any unsuccessful API requests with automatic retries, allowing up to 5 retry attempts.

Our system incorporates an exponential backoff strategy, intelligently spacing out retry attempts to prevent network overload and enhance reliability. Utilize the "retry" parameter of the API to enable this feature seamlessly.

To enable retries, you need to add the config object to include in the Inference API request. Here's a quick example of a config implement retires

config object
        "retry": {
            "attempts": 1,
            "status_code": [503,429]
attemptsstringNumber of retry attempts-Yes
status_codestringStatus codes to trigger retries-No