# `createProviderRegistry()`

When you work with multiple providers and models, it is often desirable to manage them
in a central place and access the models through simple string ids.

`createProviderRegistry` lets you create a registry with multiple providers that you
can access by their ids in the format `providerId:modelId`.

### Setup

You can create a registry with multiple providers and models using `createProviderRegistry`.

```ts
import { anthropic } from '@ai-sdk/anthropic';
import { createOpenAI } from '@ai-sdk/openai';
import { createProviderRegistry } from 'ai';

export const registry = createProviderRegistry({
  // register provider with prefix and default setup:
  anthropic,

  // register provider with prefix and custom setup:
  openai: createOpenAI({
    apiKey: process.env.OPENAI_API_KEY,
  }),
});
```

### Custom Separator

By default, the registry uses `:` as the separator between provider and model IDs. You can customize this separator by passing a `separator` option:

```ts
const registry = createProviderRegistry(
  {
    anthropic,
    openai,
  },
  { separator: ' > ' },
);

// Now you can use the custom separator
const model = registry.languageModel('anthropic > claude-3-opus-20240229');
```

### Language models

You can access language models by using the `languageModel` method on the registry.
The provider id will become the prefix of the model id: `providerId:modelId`.

```ts highlight={"5"}
import { generateText } from 'ai';
import { registry } from './registry';

const { text } = await generateText({
  model: registry.languageModel('openai:gpt-4.1'),
  prompt: 'Invent a new holiday and describe its traditions.',
});
```

### Text embedding models

You can access text embedding models by using the `textEmbeddingModel` method on the registry.
The provider id will become the prefix of the model id: `providerId:modelId`.

```ts highlight={"5"}
import { embed } from 'ai';
import { registry } from './registry';

const { embedding } = await embed({
  model: registry.textEmbeddingModel('openai:text-embedding-3-small'),
  value: 'sunny day at the beach',
});
```

### Image models

You can access image models by using the `imageModel` method on the registry.
The provider id will become the prefix of the model id: `providerId:modelId`.

```ts highlight={"5"}
import { generateImage } from 'ai';
import { registry } from './registry';

const { image } = await generateImage({
  model: registry.imageModel('openai:dall-e-3'),
  prompt: 'A beautiful sunset over a calm ocean',
});
```

## Import

<Snippet text={`import { createProviderRegistry } from "ai"`} prompt={false} />

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'providers',
      type: 'Record<string, Provider>',
      description:
        'The unique identifier for the provider. It should be unique within the registry.',
      properties: [
        {
          type: 'Provider',
          parameters: [
            {
              name: 'languageModel',
              type: '(id: string) => LanguageModel',
              description:
                'A function that returns a language model by its id.',
            },
            {
              name: 'textEmbeddingModel',
              type: '(id: string) => EmbeddingModel<string>',
              description:
                'A function that returns a text embedding model by its id.',
            },
            {
              name: 'imageModel',
              type: '(id: string) => ImageModel',
              description: 'A function that returns an image model by its id.',
            },
          ],
        },
      ],
    },
    {
      name: 'options',
      type: 'object',
      description: 'Optional configuration for the registry.',
      properties: [
        {
          type: 'Options',
          parameters: [
            {
              name: 'separator',
              type: 'string',
              description:
                'Custom separator between provider and model IDs. Defaults to ":".',
            },
          ],
        },
      ],
    },
  ]}
/>

### Returns

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

<PropertiesTable
  content={[
    {
      name: 'languageModel',
      type: '(id: string) => LanguageModel',
      description:
        'A function that returns a language model by its id (format: providerId:modelId)',
    },
    {
      name: 'textEmbeddingModel',
      type: '(id: string) => EmbeddingModel<string>',
      description:
        'A function that returns a text embedding model by its id (format: providerId:modelId)',
    },
    {
      name: 'imageModel',
      type: '(id: string) => ImageModel',
      description:
        'A function that returns an image model by its id (format: providerId:modelId)',
    },
  ]}
/>


## Navigation

- [generateText](/v5/docs/reference/ai-sdk-core/generate-text)
- [streamText](/v5/docs/reference/ai-sdk-core/stream-text)
- [generateObject](/v5/docs/reference/ai-sdk-core/generate-object)
- [streamObject](/v5/docs/reference/ai-sdk-core/stream-object)
- [embed](/v5/docs/reference/ai-sdk-core/embed)
- [embedMany](/v5/docs/reference/ai-sdk-core/embed-many)
- [generateImage](/v5/docs/reference/ai-sdk-core/generate-image)
- [transcribe](/v5/docs/reference/ai-sdk-core/transcribe)
- [generateSpeech](/v5/docs/reference/ai-sdk-core/generate-speech)
- [tool](/v5/docs/reference/ai-sdk-core/tool)
- [dynamicTool](/v5/docs/reference/ai-sdk-core/dynamic-tool)
- [experimental_createMCPClient](/v5/docs/reference/ai-sdk-core/create-mcp-client)
- [Experimental_StdioMCPTransport](/v5/docs/reference/ai-sdk-core/mcp-stdio-transport)
- [jsonSchema](/v5/docs/reference/ai-sdk-core/json-schema)
- [zodSchema](/v5/docs/reference/ai-sdk-core/zod-schema)
- [valibotSchema](/v5/docs/reference/ai-sdk-core/valibot-schema)
- [ModelMessage](/v5/docs/reference/ai-sdk-core/model-message)
- [UIMessage](/v5/docs/reference/ai-sdk-core/ui-message)
- [validateUIMessages](/v5/docs/reference/ai-sdk-core/validate-ui-messages)
- [safeValidateUIMessages](/v5/docs/reference/ai-sdk-core/safe-validate-ui-messages)
- [createProviderRegistry](/v5/docs/reference/ai-sdk-core/provider-registry)
- [customProvider](/v5/docs/reference/ai-sdk-core/custom-provider)
- [cosineSimilarity](/v5/docs/reference/ai-sdk-core/cosine-similarity)
- [wrapLanguageModel](/v5/docs/reference/ai-sdk-core/wrap-language-model)
- [LanguageModelV2Middleware](/v5/docs/reference/ai-sdk-core/language-model-v2-middleware)
- [extractReasoningMiddleware](/v5/docs/reference/ai-sdk-core/extract-reasoning-middleware)
- [simulateStreamingMiddleware](/v5/docs/reference/ai-sdk-core/simulate-streaming-middleware)
- [defaultSettingsMiddleware](/v5/docs/reference/ai-sdk-core/default-settings-middleware)
- [stepCountIs](/v5/docs/reference/ai-sdk-core/step-count-is)
- [hasToolCall](/v5/docs/reference/ai-sdk-core/has-tool-call)
- [simulateReadableStream](/v5/docs/reference/ai-sdk-core/simulate-readable-stream)
- [smoothStream](/v5/docs/reference/ai-sdk-core/smooth-stream)
- [generateId](/v5/docs/reference/ai-sdk-core/generate-id)
- [createIdGenerator](/v5/docs/reference/ai-sdk-core/create-id-generator)


[Full Sitemap](/sitemap.md)