`customProvider()`

With a custom provider, you can map ids to any model. This allows you to set up custom model configurations, alias names, and more. The custom provider also supports a fallback provider, which is useful for wrapping existing providers and adding additional functionality.

Example: custom model settings

You can create a custom provider using customProvider.

import { openai } from '@ai-sdk/openai';
import { customProvider } from 'ai';

// custom provider with different model settings:
export const myOpenAI = customProvider({
  languageModels: {
    // replacement model with custom settings:
    'gpt-5': wrapLanguageModel({
      model: openai('gpt-5'),
      middleware: defaultSettingsMiddleware({
        settings: {
          providerOptions: {
            openai: {
              reasoningEffort: 'high',
            },
          },
        },
      }),
    }),
    // alias model with custom settings:
    'gpt-4o-reasoning-high': wrapLanguageModel({
      model: openai('gpt-4o'),
      middleware: defaultSettingsMiddleware({
        settings: {
          providerOptions: {
            openai: {
              reasoningEffort: 'high',
            },
          },
        },
      }),
    }),
  },
  fallbackProvider: openai,
});

Import

import {  customProvider } from "ai"

API Signature

Parameters

languageModels?:

Record<string, LanguageModel>

.embeddingModels?:

Record<string, EmbeddingModel<string>>

imageModels?:

Record<string, ImageModel>

transcriptionModels?:

Record<string, TranscriptionModel>

speechModels?:

Record<string, SpeechModel>

rerankingModels?:

Record<string, RerankingModel>

fallbackProvider?:

Provider

Returns

The customProvider function returns a Provider instance. It has the following methods:

languageModel:

(id: string) => LanguageModel

embeddingModel:

(id: string) => EmbeddingModel<string>

imageModel:

(id: string) => ImageModel

transcriptionModel:

(id: string) => TranscriptionModel

speechModel:

(id: string) => SpeechModel

rerankingModel:

(id: string) => RerankingModel