An HTTP error describes how the endpoint handled a request; by itself, it does not show whether the advertised model is genuine. Providers and gateways can use status codes differently, so check the response and the provider's own API documentation together.
401 usually points to missing, invalid, expired, or incorrectly scoped credentials. Confirm that the key belongs to this provider, is sent in the format the API expects, and can access the requested model. Do not paste the key into logs or support posts.
403 often means the request was understood but access was denied. Check model permissions, account or project selection, IP allowlists, region restrictions, and available quota. Some gateways use 401 or 404 for the same restrictions.
404 commonly means the base path or route is wrong, or the model ID is not available on that endpoint. Copy the API base URL and exact model ID from the provider's integration documentation. Keep any documented version prefix, and do not append a route such as chat/completions to the base URL.
If the error persists, compare the request format with the endpoint documentation and try a minimal request in your own environment. A handshake failure in ModelVerify means the check could not proceed; it is not proof that the model is fake. See the setup guide for field-by-field instructions.
ModelVerify sends verification requests through your API key and they may incur provider charges. Use a restricted key where available, and review the result as evidence about observed behavior rather than an unconditional guarantee.