> ## Documentation Index
> Fetch the complete documentation index at: https://narev.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# CreatePerplexityV3Middleware

[**@ai-billing/perplexity**](../index)

***

[@ai-billing/perplexity](/docs/sdk/ai-billing/reference/perplexity/typedoc/index) / createPerplexityV3Middleware

# Function: createPerplexityV3Middleware()

> **createPerplexityV3Middleware**\<`TTags`>(`options`): `LanguageModelV3Middleware`

Defined in: [perplexity/src/ai-sdk/language-model-middleware/v3/language-model-v3-perplexity-billing-middleware.ts:99](https://github.com/narevai/ai-billing/blob/main/packages/perplexity/src/ai-sdk/language-model-middleware/v3/language-model-v3-perplexity-billing-middleware.ts#L99)

Creates a V3 billing middleware for the Perplexity provider (`@ai-sdk/perplexity`).
Perplexity has no prompt-caching feature, so cache-read/cache-write tokens are always reported as `0`.
All Perplexity `sonar` models are web-search-grounded and bill a flat per-request search fee
(`request_cost`) on top of token costs — see calculatePerplexityCost for how that is modeled.

## Type Parameters

### TTags

`TTags` *extends* `JSONObject`

The shape of the tags object, extending DefaultTags.

## Parameters

### options

[`PerplexityV3MiddlewareOptions`](/docs/sdk/ai-billing/reference/perplexity/typedoc/interfaces/PerplexityV3MiddlewareOptions)\<`TTags`>

Billing options; see [PerplexityV3MiddlewareOptions](/docs/sdk/ai-billing/reference/perplexity/typedoc/interfaces/PerplexityV3MiddlewareOptions). A `priceResolver` is required.

## Returns

`LanguageModelV3Middleware`

A V3 billing middleware instance for Perplexity.

## Example

```ts theme={null}
import { createPerplexity } from '@ai-sdk/perplexity';
import { wrapLanguageModel } from 'ai';
import { createPerplexityV3Middleware } from '@ai-billing/perplexity';
import {
  consoleDestination,
  createObjectPriceResolver,
  type ModelPricing,
} from '@ai-billing/core';

const perplexity = createPerplexity({ apiKey: process.env.PERPLEXITY_API_KEY });

const customPricingMap: Record<string, ModelPricing> = {
  'sonar-pro': {
    promptTokens: 3.0 / 1_000_000,
    completionTokens: 15.0 / 1_000_000,
    request: 6.0 / 1_000, // flat per-request search fee (low search_context_size rate)
  },
};

const priceResolver = createObjectPriceResolver(customPricingMap);

const billingMiddleware = createPerplexityV3Middleware({
  destinations: [consoleDestination()],
  priceResolver,
});

const wrappedModel = wrapLanguageModel({
  model: perplexity('sonar-pro'),
  middleware: billingMiddleware,
});
```