Class GenerateContentRequest

Generates a response from the model given an input GenerateContentRequest. Input capabilities differ between models, including tuned models.See the model guide and tuning guide for details.

Inheritance
object
GoogleGeminiRequest
GenerateContentRequest
Implements
Inherited Members
Namespace: Glitch9.AIDevKit.Google
Assembly: Glitch9.AIDevKit.Provider.Google.dll
Syntax
public sealed class GenerateContentRequest : GoogleGeminiRequest, IJsonRequest, IValidatable
Remarks

Lastest parameters confirmed on 2025.12.17

Properties

| Edit this page View Source

CachedContent

Optional. The name of the cached content used as context to serve the prediction.

Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings.

Format: cachedContents/{cachedContent}

Declaration
[JsonProperty("cachedContent")]
public string CachedContent { get; set; }
Property Value
Type Description
string
| Edit this page View Source

Config

Optional. Configuration options for model generation and outputs.

Declaration
[JsonProperty("generationConfig")]
public GeminiConfig Config { get; set; }
Property Value
Type Description
GeminiConfig
| Edit this page View Source

Contents

Required. The content of the current conversation with the model. For single-turn queries, this is a single instance.For multi-turn queries, this is a repeated field that contains conversation history + latest request.

Declaration
[JsonProperty("contents")]
public List<GeminiContent> Contents { get; set; }
Property Value
Type Description
List<GeminiContent>
| Edit this page View Source

SafetySettings

Optional.

A list of unique SafetySetting instances for blocking unsafe content.

This will be enforced on the Contents and Candidates. There should not be more than one setting for each SafetyCategory type. The API will block any contents and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each SafetyCategory specified in the safetySettings. If there is no SafetySetting for a given SafetyCategory provided in the list, the API will use the default safety setting for that category. Harm categories Hate, Sexual, Dangerous, Harassment are supported.

Declaration
[JsonProperty("safetySettings")]
public List<SafetySetting> SafetySettings { get; set; }
Property Value
Type Description
List<SafetySetting>
| Edit this page View Source

SystemInstruction

Optional. (Beta) Developer set system instruction. Currently, text only.

Declaration
[JsonProperty("systemInstruction")]
public GeminiContent SystemInstruction { get; set; }
Property Value
Type Description
GeminiContent
| Edit this page View Source

ToolConfig

Optional. Tool configuration for any Tool (Tools) specified in the request.

Declaration
[JsonProperty("toolConfig")]
public ToolConfig ToolConfig { get; set; }
Property Value
Type Description
ToolConfig
| Edit this page View Source

Tools

Optional. (Beta) A list of GeminiTool the model may use to generate the next response.

Declaration
[JsonProperty("tools")]
public List<GeminiTool> Tools { get; set; }
Property Value
Type Description
List<GeminiTool>

Methods

| Edit this page View Source

IsValid()

Declaration
public bool IsValid()
Returns
Type Description
bool
| Edit this page View Source

Validate()

Validates the object's parameters and throws if invalid.

Declaration
public void Validate()

Implements

Extension Methods