ChatGenerationParams | OpenRouter TypeScript SDK | OpenRouter

The TypeScript SDK and docs are currently in beta. Report issues on GitHub.

Example Usage

1 import { ChatGenerationParams } from "@openrouter/sdk/models";
2 
3 let value: ChatGenerationParams = {
4   messages: [
5     {
6       role: "system",
7       content: "<value>",
8     },
9   ],
10 };

Fields

Field	Type	Required	Description
`provider`	models.ChatGenerationParamsProvider	➖	When multiple model providers are available, optionally indicate your routing preference.
`plugins`	models.ChatGenerationParamsPluginUnion[]	➖	Plugins you want to enable for this request, including their settings.
`route`	models.ChatGenerationParamsRoute	➖	Routing strategy for multiple models: “fallback” (default) uses secondary models as backups, “sort” sorts all endpoints together by routing criteria.
`user`	string	➖	N/A
`sessionId`	string	➖	A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 128 characters.
`messages`	models.Message[]	✔️	N/A
`model`	string	➖	N/A
`models`	string[]	➖	N/A
`frequencyPenalty`	number	➖	N/A
`logitBias`	`Record<string, number>`	➖	N/A
`logprobs`	boolean	➖	N/A
`topLogprobs`	number	➖	N/A
`maxCompletionTokens`	number	➖	N/A
`maxTokens`	number	➖	N/A
`metadata`	`Record<string, string>`	➖	N/A
`presencePenalty`	number	➖	N/A
`reasoning`	models.Reasoning	➖	N/A
`responseFormat`	models.ChatGenerationParamsResponseFormatUnion	➖	N/A
`seed`	number	➖	N/A
`stop`	models.ChatGenerationParamsStop	➖	N/A
`stream`	boolean	➖	N/A
`streamOptions`	models.ChatStreamOptions	➖	N/A
`temperature`	number	➖	N/A
`toolChoice`	any	➖	N/A
`tools`	models.ToolDefinitionJson[]	➖	N/A
`topP`	number	➖	N/A
`debug`	models.Debug	➖	N/A