Skip to main content
@ai-billing/chutes
@ai-billing/chutes / createChutesV3Middleware

​
Function: createChutesV3Middleware()

createChutesV3Middleware<TTags>(options): LanguageModelV3Middleware
Defined in: chutes/src/ai-sdk/language-model-middleware/v3/language-model-v3-chutes-billing-middleware.ts:78 Creates a V3 billing middleware for the Chutes provider (llm.chutes.ai via @ai-sdk/openai-compatible). Deducts cache-read tokens from prompt tokens before billing — Chutes charges only non-cached input at the prompt rate, and cached tokens separately at the cache-read rate.

​
Type Parameters

​
TTags

TTags extends JSONObject The shape of the tags object, extending DefaultTags.

​
Parameters

​
options

ChutesV3MiddlewareOptions<TTags> Billing options; see ChutesV3MiddlewareOptions. A priceResolver is required.

​
Returns

LanguageModelV3Middleware A V3 billing middleware instance for Chutes.

​
Example

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { wrapLanguageModel } from 'ai';
import { createChutesMiddleware } from '@ai-billing/chutes';
import {
  consoleDestination,
  createObjectPriceResolver,
  type ModelPricing,
} from '@ai-billing/core';
import type { LanguageModelV3 } from '@ai-sdk/provider';

const chutes = createOpenAICompatible({
  name: 'chutes',
  baseURL: 'https://llm.chutes.ai/v1',
  apiKey: process.env.CHUTES_API_KEY,
});

const customPricingMap: Record<string, ModelPricing> = {
  'deepseek-ai/DeepSeek-V3-0324': {
    promptTokens: 0.27 / 1_000_000,
    completionTokens: 1.10 / 1_000_000,
    inputCacheReadTokens: 0.07 / 1_000_000,
  },
};

const priceResolver = createObjectPriceResolver(customPricingMap);

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

const wrappedModel = wrapLanguageModel({
  model: chutes('deepseek-ai/DeepSeek-V3-0324') as unknown as LanguageModelV3,
  middleware: billingMiddleware,
});