Use the endpoint and model identifier that your application sends to the provider. Dashboard pages, model marketing names, and API request values can be different.
Find the Base URL in the provider's API or integration documentation. Copy the documented API root, including a required version prefix such as /v1. Do not use the provider dashboard URL, and do not include the full operation path or query string. Providers can use different base paths, so do not add /v1 unless their docs specify it.
Find the model ID in the provider's API reference, model list, or the configuration that already works in your application. Copy the exact value sent as the request's model field, including provider-specific aliases and version suffixes. Preserve its spelling and punctuation.
If a model-list endpoint is available, it may show only the models visible to the current key or project. A model can be advertised by name but unavailable to your account or region; confirm access with the provider before treating a not-found response as a configuration mistake.
The official reference model in ModelVerify is a separate selection from the provider's model ID. Choose the reference you intend to compare against, then verify that the endpoint and protocol match the provider's documentation. Read the setup guide for the complete submission flow.
Verification requests use your API key and may incur provider charges. Prefer a restricted key with only the required access and quota.