> ## 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.

# PrivateEndpointSettings

Capabilities and limits routing uses for this endpoint. A new endpoint copies them from the public endpoint for the same model and provider, or from the model, and the owner can change them. Rate limits are not part of this object: a private endpoint is billed to its own upstream key, so request limits stay with the provider.

## Example Usage

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

let value: PrivateEndpointSettings = {
  completions: {
    chat: true,
    text: false,
  },
  contextLength: 128000,
  excludedParameters: [
    "logit_bias",
  ],
  inputs: {
    audio: false,
    base64Files: null,
    base64Images: true,
    fileUrls: null,
    imageUrls: true,
  },
  maxCompletionTokens: 16384,
  maxPromptTokens: null,
  quantization: "bf16",
  reasoning: {
    returnMechanism: "reasoning",
    supported: true,
  },
  toolChoice: {
    auto: true,
    function: false,
    none: true,
    required: true,
  },
};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `completions` | [models.PrivateEndpointSettingsCompletions](../models/privateendpointsettingscompletions.mdx) | ✔️ | N/A | |
| `contextLength` | *number* | ✔️ | Longest prompt plus completion, in tokens, or `null` to keep the model default. | 128000 |
| `excludedParameters` | [models.PrivateEndpointSettingsExcludedParameter](../models/privateendpointsettingsexcludedparameter.mdx)\[] | ✔️ | Request parameters the upstream rejects even though the model supports them; requests using one do not route here. Cannot name a tested parameter. | \[ "logit\_bias" ] |
| `inputs` | [models.PrivateEndpointSettingsInputs](../models/privateendpointsettingsinputs.mdx) | ✔️ | N/A | |
| `maxCompletionTokens` | *number* | ✔️ | Longest completion the upstream returns, in tokens, or `null` to keep the model default. | 16384 |
| `maxPromptTokens` | *number* | ✔️ | Longest prompt, in tokens, or `null` for no cap below the context length. Cannot exceed `context_length`, or the model context length while `context_length` is `null`. | null |
| `quantization` | [models.PrivateEndpointQuantization](../models/privateendpointquantization.mdx) | ✔️ | Weight precision the deployment runs at; `unknown` when not stated. | bf16 |
| `reasoning` | [models.PrivateEndpointSettingsReasoning](../models/privateendpointsettingsreasoning.mdx) | ✔️ | N/A | |
| `toolChoice` | [models.PrivateEndpointSettingsToolChoice](../models/privateendpointsettingstoolchoice.mdx) | ✔️ | N/A | |