> ## 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.

# CreateCerebrasV4Middleware

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

***

[@ai-billing/cerebras](/docs/sdk/ai-billing/reference/cerebras/typedoc/index) / createCerebrasV4Middleware

# Function: createCerebrasV4Middleware()

> **createCerebrasV4Middleware**\<`TTags`>(`options`): `LanguageModelV4Middleware`

Defined in: [cerebras/src/ai-sdk/language-model-middleware/v4/language-model-v4-cerebras-billing-middleware.ts:95](https://github.com/narevai/ai-billing/blob/main/packages/cerebras/src/ai-sdk/language-model-middleware/v4/language-model-v4-cerebras-billing-middleware.ts#L95)

Creates a V4 billing middleware for the Cerebras provider (`@ai-sdk/cerebras`).
Deducts cache-read tokens from prompt tokens and reasoning tokens from completion tokens before
billing the base rates — Cerebras charges only non-cached input at the prompt rate, cached input
separately at the cache-read rate, and reasoning tokens (a subset of `completion_tokens`) at the
completion rate.

## Type Parameters

### TTags

`TTags` *extends* `JSONObject`

The shape of the tags object, extending DefaultTags.

## Parameters

### options

[`CerebrasV4MiddlewareOptions`](/docs/sdk/ai-billing/reference/cerebras/typedoc/interfaces/CerebrasV4MiddlewareOptions)\<`TTags`>

Billing options; see [CerebrasV4MiddlewareOptions](/docs/sdk/ai-billing/reference/cerebras/typedoc/interfaces/CerebrasV4MiddlewareOptions). A `priceResolver` is required.

## Returns

`LanguageModelV4Middleware`

A V4 billing middleware instance for Cerebras.

## Example

```ts theme={null}
import { createCerebras } from '@ai-sdk/cerebras';
import { wrapLanguageModel } from 'ai';
import { createCerebrasV4Middleware } from '@ai-billing/cerebras';
import {
  consoleDestination,
  createObjectPriceResolver,
  type ModelPricing,
} from '@ai-billing/core';

const cerebras = createCerebras({ apiKey: process.env.CEREBRAS_API_KEY });

const customPricingMap: Record<string, ModelPricing> = {
  // NOTE: unverified estimate — confirm against https://www.cerebras.ai/pricing before shipping.
  'gpt-oss-120b': {
    promptTokens: 0.25 / 1_000_000,
    completionTokens: 0.69 / 1_000_000,
  },
};

const priceResolver = createObjectPriceResolver(customPricingMap);

const billingMiddleware = createCerebrasV4Middleware({
  destinations: [consoleDestination()],
  priceResolver,
});

const wrappedModel = wrapLanguageModel({
  model: cerebras('gpt-oss-120b'),
  middleware: billingMiddleware,
});
```