--- title: "ProviderResponse" --- Details of a provider response for a generation attempt ## Fields | Field | Type | Required | Description | Example | | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | `endpoint_id` | *Optional[str]* | :heavy_minus_sign: | Internal endpoint identifier | ep_abc123 | | `id` | *Optional[str]* | :heavy_minus_sign: | Upstream provider response identifier | chatcmpl-abc123 | | `is_byok` | *Optional[bool]* | :heavy_minus_sign: | Whether the request used a bring-your-own-key | false | | `latency` | *Optional[float]* | :heavy_minus_sign: | Response latency in milliseconds | 1200 | | `model_permaslug` | *Optional[str]* | :heavy_minus_sign: | Canonical model slug | openai/gpt-4 | | `provider_name` | [Optional[components.ProviderResponseProviderName]](../components/providerresponseprovidername.mdx) | :heavy_minus_sign: | Name of the provider | OpenAI | | `status` | *Nullable[int]* | :heavy_check_mark: | HTTP status code from the provider | 200 |