Providers And Registry
Vercel AI SDK (`ai` npm package) · Vercel AI SDK
AI SDK — Vercel AI SDK
Evaluates Vercel AI SDK's Providers & Provider Registry across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI SDK eval coverage.
About Vercel AI SDK
Vercel AI SDK is the open-source TypeScript-first AI framework from Vercel — the `ai` npm package. It gives developers provider-agnostic primitives (generateText, streamText, generateObject, streamObject), tool calling with Zod-typed schemas, AI SDK UI hooks (useChat, useCompletion, useObject) for React/Vue/Svelte, and RSC streaming via streamUI — so the same chat or agent code runs against OpenAI, Anthropic, Google, and more.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | 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). | Pass / FailAi Platformhigh |
| 02 | 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') }). | Pass / FailAi Platformmedium |
| 03 | 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. | Pass / FailAi Platformmedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Vercel Ai Sdk
- Ai Platform
- Providers And Registry
Recommended for
Works with
Related evals
Browserbase
Evaluates Browserbase's Captcha Handling across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Concurrency & Rate Limits across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Live Debugging & Session Inspector across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
ViewFrequently asked questions
What does the Providers And Registry eval for Vercel AI SDK Vercel AI SDK (`ai` npm package) test?+
Evaluates Vercel AI SDK's Providers & Provider Registry across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI SDK eval coverage.
How is the Providers And Registry eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Providers And Registry pack for Vercel AI SDK Vercel AI SDK (`ai` npm package) contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Providers And Registry pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.