For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
ModelsChatRankingsDocs
DocsAPI ReferenceClient SDKsAgent SDKCookbookChangelog
DocsAPI ReferenceClient SDKsAgent SDKCookbookChangelog
    • Overview
    • Usage for Agents
  • TypeScript SDK
    • Overview
      • Analytics
      • APIKeys
      • Byok
      • Chat
      • Credits
      • Embeddings
      • Endpoints
      • Generations
      • Guardrails
      • OAuth
      • Observability
        • CreateRerankRequestBody
      • Organization
      • Presets
      • Providers
      • Rerank
      • Beta.Responses
      • Transcriptions
      • Speech
      • VideoGeneration
      • Workspaces
  • Python SDK
    • Overview
  • Go SDK
  • DevTools
    • Overview
    • Migrating to @openrouter/agent
LogoLogo
ModelsChatRankingsDocs
On this page
  • Example Usage
  • Fields
TypeScript SDKAPI ReferenceOperations

CreateRerankRequestBody - TypeScript SDK

CreateRerankRequestBody type definition
Was this page helpful?
Previous

Organization - TypeScript SDK

Organization method reference
Next
Built with

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

Rerank request input

Example Usage

1import { CreateRerankRequestBody } from "@openrouter/sdk/models/operations";
2
3let value: CreateRerankRequestBody = {
4 documents: [
5 "Paris is the capital of France.",
6 "Berlin is the capital of Germany.",
7 ],
8 model: "cohere/rerank-v3.5",
9 query: "What is the capital of France?",
10};

Fields

FieldTypeRequiredDescriptionExample
documentsstring[]✔️The list of documents to rerank[
“Paris is the capital of France.”,
“Berlin is the capital of Germany.”
]
modelstring✔️The rerank model to usecohere/rerank-v3.5
providermodels.ProviderPreferences➖N/A{"allow_fallbacks": true}
querystring✔️The search query to rerank documents againstWhat is the capital of France?
topNnumber➖Number of most relevant documents to return3