Sign in
← AI PulseAug 4, 2026

Wire · news · Single-source brief

Vercel AI SDK Updates Baseten Integration for Embeddings

The Vercel AI SDK has updated its Baseten integration, making the native performance client for embeddings an opt-in feature and removing it as a default dependency.

By Illumora Editorial

Source · Aug 4, 2026, 5:16 AM · On Illumora · Aug 4, 2026, 5:27 AM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →Vercel AI SDK Changelog — Release @ai-sdk/workflow-harness@1.0.57 · vercel/ai
Save

The Vercel AI SDK has released an update to its Baseten integration, specifically for embeddings. This change, part of the @ai-sdk/baseten@2.1.0 release, makes the native performance client an opt-in component rather than a default dependency.

Key Points

  • The @ai-sdk/baseten@2.1.0 release includes a minor change to the Baseten integration.
  • The native performance client for embeddings is now opt-in.
  • @basetenlabs/performance-client is no longer a default dependency.
  • The previous client was a NAPI addon, comprising 16 platform binary packages and 5-16 MB in size.
  • The prior client could not load in edge runtimes and its platform binaries were difficult for bundlers to resolve.
  • Embeddings now use plain HTTP to the deployment's OpenAI-compatible endpoint.
  • Users can install the native client themselves and pass its constructor to createBaseten to retain client-side batching and request hedging.

Context

According to the Vercel AI SDK changelog, the previous native performance client for embeddings was a significant dependency. It was a NAPI addon that included multiple platform binary packages, consuming a notable amount of disk space. This client also presented compatibility issues with edge runtimes and bundlers, and its top-level module import meant all consumers incurred its cost, even if they did not use embeddings.

Why It Matters

This update simplifies the dependency structure for developers using the Vercel AI SDK with Baseten, particularly for those not utilizing embeddings or deploying to edge environments. It reduces the default package size and resolves compatibility issues, while still offering the option to use the performance client for specific use cases.

What To Do

  • Note that @basetenlabs/performance-client is no longer a default dependency for @ai-sdk/baseten@2.1.0.
  • If using Baseten embeddings and requiring client-side batching or request hedging, install @basetenlabs/performance-client separately.
  • Pass the PerformanceClient constructor to createBaseten when initializing the Baseten client.
  • Review your project's dependencies if you are upgrading to @ai-sdk/baseten@2.1.0.