Error Reference

You may encounter errors when working with the API. This page describes how errors are reported and lists the most common error codes.

How Errors Are Reported

If some providers returned with errors but PurAI found a valid response, there will be a cache field in the response body.

If all providers returned with errors, the API will return with 500 Internal Server Error with all cached errors.

In Response Body


...
"cache": {
    "status": 500,
    "error": {
        "message": "Some of our providers returned with errors. Errors are automatically reported to our developers.",
        "records": [
            {
                "provider": "provider-1",
                "response": {
                    "status": 404,
                    "data": "404 Not Found"
                }
            },
            {
                "provider": "provider-2",
                "response": {
                    "status": 504,
                    "data": "timeout of 60000ms exceeded"
                }
            },
            {
                "provider": "provider-3",
                "response": {
                    "status": 504,
                    "data": "timeout of 60000ms exceeded"
                }
            }
        ]
    }
},
...

Direct Error

Provider Errors


{
	"status": 500,
	"error": {
	    "message": "All of our providers returned with errors. Errors are automatically reported to our developers.",
	    "records": [...]
	}
}

Other Errors


{
    "status": 503,
    "error": "Model is not available at the moment."
}

List of Common Errors

Error	Description
`400` Bad Request	Endpoint not found or not available for this model, personality only available for the `/openai/chat/completions` endpoint or Model is blocked by personality. Available models for this personality: (…)
`401` Unauthorized	Authentication credentials are missing, invalid, or expired: check your API key
`403` Forbidden	The request is valid, but the client does not have the necessary permissions to access the requested resource.
`404` Not Found	The requested resource could not be found on the server: model not found, or personality not found.
`405` Method Not Allowed	The `HTTP` method (`GET`, `POST`, `PUT`, `DELETE`, etc.) used in the request is not supported for the specified resource.
`429` Too Many Requests	The user has sent too many requests, and the server is rate-limiting the client to prevent abuse.
`500` Internal Server Error	An unexpected condition was encountered on the server, and no more specific message is suitable to convey the exact nature of the problem. Usually occurs when all our providers return with errors.
`502` Bad Gateway	The server acting as a gateway or proxy received an invalid response from the upstream server while trying to fulfill the request.
`503` Service Unavailable	The server is not ready to handle the request: Model is not available at the moment.
`504` Gateway Timeout	The server acting as a gateway or proxy did not receive a timely response from the upstream server or another auxiliary server while trying to load the URL.

Every error response also includes a short message that indicates what went wrong:

Response


{
	"status": 500,
	"error": {
	"message": "All of our providers returned with errors. Errors are automatically reported to our developers.",
	"records": [...]
	}
}