Errors

The API uses standard HTTP status codes and returns consistent error response bodies. All errors include a machine-readable error code and a human-readable message.

Error Response Format

All errors return a JSON object with an error field containing the error code, message, and HTTP status.

HTTP Status Codes

Code	Meaning
`200`	Success
`400`	Bad Request -- Invalid parameters or malformed request body
`401`	Unauthorized -- Invalid or missing API key
`402`	Payment Required -- Insufficient credits to complete the request
`403`	Forbidden -- Insufficient permissions
`404`	Not Found -- Resource does not exist
`409`	Conflict -- Resource already exists (e.g., duplicate email)
`429`	Too Many Requests -- Rate limit exceeded
`500`	Internal Server Error

Error Codes

Code	HTTP Status	Description
`BAD_REQUEST`	`400`	The request body is malformed or missing required fields
`UNAUTHORIZED`	`401`	The API key is invalid, missing, or has been revoked
`INSUFFICIENT_CREDITS`	`402`	Your account has insufficient credits. Please top up before retrying.
`FORBIDDEN`	`403`	You do not have permission to access this resource
`NOT_FOUND`	`404`	The requested resource was not found
`CONFLICT`	`409`	A resource conflict occurred (e.g., duplicate registration)
`RATE_LIMIT_EXCEEDED`	`429`	You have exceeded your rate limit. Wait and retry using the Retry-After header.
`MODEL_NOT_FOUND`	`400`	The specified model does not exist or is inactive. Use GET /v1/models to list available models.
`UPSTREAM_ERROR`	`502`	An upstream service (search, citation, etc.) returned an error or timed out
`PROVIDER_ERROR`	`502`	The LLM provider returned an error (e.g., content filtered, context too long)
`BILLING_ERROR`	`500`	A billing system error occurred during credit hold/settle
`SEARCH_FAILED`	`500`	Paper search execution failed
`ANALYSIS_FAILED`	`500`	Paper analysis execution failed
`INTERNAL_ERROR`	`500`	An unexpected error occurred on our end

Example

import requests

response = requests.post(
    "https://api.qinyanai.com/v1/paper-search/google",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"query": "machine learning"}
)

if response.status_code != 200:
    error = response.json()["error"]
    print(f"Error {error['code']}: {error['message']}")
else:
    data = response.json()
    print(f"Found {len(data['data'])} papers")

Response

{
  "error": {
    "code": "INSUFFICIENT_CREDITS",
    "message": "Insufficient credits: available=0.50, required=1.00",
    "detail": null
  }
}