> ## 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.
# CreateRerankRequestBody
Rerank request input
## Example Usage
```typescript theme={null}
import { CreateRerankRequestBody } from "@openrouter/sdk/models/operations";
let value: CreateRerankRequestBody = {
documents: [
"Paris is the capital of France.",
"Berlin is the capital of Germany.",
],
model: "cohere/rerank-v3.5",
query: "What is the capital of France?",
};
```
## Fields
| Field | Type | Required | Description | Example |
| ----------- | ------------------------------------------------------------------ | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| `documents` | *operations.Document*\[] | :heavy\_check\_mark: | The list of documents to rerank. Documents may be plain strings, or structured objects with `text` and/or `image` for multimodal models. | \[
"Paris is the capital of France.",
"Berlin is the capital of Germany."
] |
| `model` | *string* | :heavy\_check\_mark: | The rerank model to use | cohere/rerank-v3.5 |
| `provider` | [models.ProviderPreferences](../../models/providerpreferences.mdx) | :heavy\_minus\_sign: | N/A | \{
"allow\_fallbacks": true
} |
| `query` | *string* | :heavy\_check\_mark: | The search query to rerank documents against | What is the capital of France? |
| `topN` | *number* | :heavy\_minus\_sign: | Number of most relevant documents to return | 3 |