Fields
| Field | Type | Required | Description | Example |
|---|---|---|---|---|
Completions | *components.UpdatePrivateEndpointSettingsRequestCompletions | ➖ | N/A | |
ContextLength | optionalnullable.OptionalNullable[int64] | ➖ | Longest prompt plus completion, in tokens, or null to keep the model default. | 128000 |
ExcludedParameters | []components.UpdatePrivateEndpointSettingsRequestExcludedParameter | ➖ | 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 | *components.UpdatePrivateEndpointSettingsRequestInputs | ➖ | N/A | |
MaxCompletionTokens | optionalnullable.OptionalNullable[int64] | ➖ | Longest completion the upstream returns, in tokens, or null to keep the model default. | 16384 |
MaxPromptTokens | optionalnullable.OptionalNullable[int64] | ➖ | 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 | *components.PrivateEndpointQuantization | ➖ | Weight precision the deployment runs at; unknown when not stated. | bf16 |
Reasoning | *components.UpdatePrivateEndpointSettingsRequestReasoning | ➖ | N/A | |
ToolChoice | *components.UpdatePrivateEndpointSettingsRequestToolChoice | ➖ | N/A |