> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# PrivateEndpoint

## Example Usage

```typescript theme={null}
import { PrivateEndpoint } from "@openrouter/sdk/models";

let value: PrivateEndpoint = {
  baseUrl: "https://contoso.openai.azure.com",
  declaredParameters: [
    "temperature",
    "seed",
  ],
  declaredRegion: "us",
  declaredZdr: true,
  id: "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
  modelName: "OpenAI: GPT-4o",
  modelPermaslug: "openai/gpt-4o-2024-08-06",
  modelSlug: "openai/gpt-4o",
  pricing: {
    completion: "0.00001",
    prompt: "0.0000025",
  },
  providerName: "Azure",
  providerSlug: "azure",
  status: "active",
  testedParameters: [
    "tools",
    "tool_choice",
    "response_format",
  ],
  upstreamModelId: "gpt-4o-prod",
};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `baseUrl` | *string* | ✔️ | HTTPS base URL of your deployment, or `null` for providers whose URL is derived from the BYOK credential (Azure, Amazon Bedrock, Google Vertex). | [https://contoso.openai.azure.com](https://contoso.openai.azure.com) |
| `declaredParameters` | *string*\[] | ✔️ | Parameters you declared the upstream supports. Requests that use a parameter only route to this endpoint when it is tested or declared. | \[ "temperature", "seed" ] |
| `declaredRegion` | [models.PrivateEndpointDeclaredRegion](../models/privateendpointdeclaredregion.mdx) | ✔️ | Where you attest this deployment processes data. `global` means not regional; `null` means undeclared. | us |
| `declaredZdr` | *boolean* | ✔️ | Whether you attest this deployment retains no prompt or completion data. `null` means undeclared. | true |
| `id` | *string* | ✔️ | Stable identifier of the private endpoint. | 5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11 |
| `maxCompletionTokens` | *number* | ➖ | Most completion tokens a request routed to this endpoint can produce, or `null` when the endpoint sets no cap beyond the model context length. | 131072 |
| `modelName` | *string* | ✔️ | Display name of the model, or `null` when the model is no longer listed. | OpenAI: GPT-4o |
| `modelPermaslug` | *string* | ✔️ | Permanent slug of the model this endpoint serves. | openai/gpt-4o-2024-08-06 |
| `modelSlug` | *string* | ✔️ | Public model slug, or `null` when the model is no longer listed. | openai/gpt-4o |
| `pricing` | [models.PrivateEndpointPricing](../models/privateendpointpricing.mdx) | ✔️ | Negotiated per-token rates reported for requests routed to this endpoint. | \{ "cache\_read": "0.00000025", "cache\_write": "0.000003125", "completion": "0.00001", "prompt": "0.0000025" } |
| `providerName` | *string* | ✔️ | Display name of the upstream provider. | Azure |
| `providerSlug` | *string* | ✔️ | Slug of the upstream provider, or `null` when the provider is no longer listed. | azure |
| `status` | [models.PrivateEndpointStatus](../models/privateendpointstatus.mdx) | ✔️ | Lifecycle state. `draft` endpoints are not routable until validated and activated; `disabled` endpoints are activated but temporarily not routable. | active |
| `testedParameters` | *string*\[] | ✔️ | Parameters a validation run proved the upstream honors (`tools`, `tool_choice`, `response_format`, `structured_outputs`, `stop`). Read-only; cleared when the upstream configuration changes. | \[ "tools", "tool\_choice", "response\_format" ] |
| `upstreamModelId` | *string* | ✔️ | Model or deployment identifier sent to the upstream provider. | gpt-4o-prod |