Sign in
← AI PulseAug 4, 2026

Wire · news · Multi-source brief

Vercel AI SDK Baseten Integration Updates Embeddings Client

The Vercel AI SDK has released version 2.1.0 of its @ai-sdk/baseten package, making the native performance client for embeddings an opt-in feature.

By Illumora Editorial

Source · Aug 4, 2026, 5:16 AM · On Illumora · Aug 4, 2026, 5:28 AM

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

Synthesized from multiple allowlisted primaries on the same event. 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/voyage@2.0.20 · vercel/ai
Save

The Vercel AI SDK has updated its @ai-sdk/baseten package to version 2.1.0, changing how the native performance client for embeddings is handled. This update, noted across releases for @ai-sdk/voyage@2.0.20, @ai-sdk/vue@4.0.51, and @ai-sdk/workflow-harness@1.0.57, makes the @basetenlabs/performance-client an opt-in dependency.

Key Points

  • The @ai-sdk/baseten package is now at version 2.1.0.
  • 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.
  • These packages ranged from 5 to 16 MB in size.
  • The prior client could not load in edge runtimes and had bundler resolution issues for its platform binaries.
  • Embeddings now use plain HTTP to the deployment's OpenAI-compatible endpoint.
  • The Baseten Embeddings Inference serves this endpoint without additional settings.
  • To retain client-side batching and request hedging, users must install PerformanceClient themselves.

Context

According to the Vercel AI SDK changelog, the @basetenlabs/performance-client was previously imported at the module top level, meaning every consumer incurred its cost even if only embeddings utilized it. The client's nature as a NAPI addon, with its substantial binary package count and size, also presented compatibility challenges, particularly in edge runtime environments.

Why It Matters

This change offers developers greater control over their dependency footprint and improves compatibility with edge runtimes when using the Vercel AI SDK's Baseten integration. It allows developers to selectively include the performance client only when its specific features, such as client-side batching and request hedging, are required.

What To Do

  • Note that @basetenlabs/performance-client is no longer a default dependency for @ai-sdk/baseten.
  • If client-side batching or request hedging are needed for embeddings, install @basetenlabs/performance-client explicitly.
  • Review the provided code example for integrating PerformanceClient when creating a Baseten instance.
  • Test existing deployments to ensure embedding functionality remains as expected after updating @ai-sdk/baseten to version 2.1.0.

Keep Exploring

/studio?pack=foundation