Providers And Registry

Operator imports `import { anthropic } from '@ai-sdk/anthropic'` and ships; production logs show MODULE_NOT_FOUND because only `ai` was installed.

Each provider is a separate npm package: `npm install @ai-sdk/anthropic` (or openai/google/mistral/azure). The `ai` core package only ships the interface; provider plugins implement LanguageModelV2. Pin compatible versions (provider plugin major must match `ai` major).

Operator wants to use a self-hosted OpenAI-compatible endpoint (e.g., a local llama.cpp server) via @ai-sdk/openai.

Use `createOpenAI({ baseURL: 'http://localhost:8080/v1', apiKey: '...' })` to produce a provider instance pointing at the custom endpoint. Do not mutate globals or set OPENAI_API_BASE env (that affects every importer). Pass the instance explicitly to generateText({ model: myOpenAI('gpt-4o') }).

Operator builds a custom provider that aliases short names to specific model ids and wants unaliased ids to pass through to the default openai provider.

Use `customProvider({ languageModels: { 'fast': openai('gpt-4o-mini'), 'deep': anthropic('claude-opus-4-5') }, fallbackProvider: openai })`. Unmatched ids resolve via fallbackProvider. Without fallbackProvider, unmatched ids throw NoSuchModelError.