Sign in
← AI PulseSep 8, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates Batch Model Support and Tool Choice Enforcement

Vercel's AI SDK, version ai@7.0.94, now supports per-request models in batch operations and enforces tool choices within streamText functions.

By Illumora Editorial

Source · Sep 8, 2026, 7:18 PM · On Illumora · Sep 8, 2026, 7:34 PM

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/harness-codex@1.0.105 · vercel/ai
Save

Vercel has released updates to its AI SDK, specifically version ai@7.0.94, introducing new features and fixes. These changes include enhanced model handling for batch requests and improved reliability for image result processing.

Key Points

  • The ai@7.0.94 release supports per-request models in batch operations.
  • Tool choices are now enforced in the streamText function.
  • The SDK retries unclassified empty image results.
  • Retry-attempt accounting is preserved for image results.
  • A provider-independent result retryability classification has been added.
  • Google and Google Vertex prompt blocks are marked as terminal.
  • Dependencies for @ai-sdk/provider@4.0.11, @ai-sdk/gateway@4.0.76, @ai-sdk/provider-utils@5.0.37, and @ai-sdk/alibaba@2.0.42 have been updated.

Context

According to the Vercel AI SDK Changelog, these updates are part of routine patch changes. The changes aim to improve the flexibility and robustness of the SDK, particularly in how it handles model requests and processes image-related outputs. The updates also affect specific provider packages like @ai-sdk/amazon-bedrock@5.0.77.

Why It Matters

These updates provide developers with more granular control over model selection in batch processes and ensure more predictable behavior when using tool choices in streaming text applications. The improvements in image result handling and retry mechanisms can lead to more stable and reliable AI-powered applications.

What To Do

  • Review the updated dependency versions for @ai-sdk/provider, @ai-sdk/gateway, @ai-sdk/provider-utils, @ai-sdk/alibaba, and @ai-sdk/amazon-bedrock.
  • Test batch operations with per-request models to leverage the new support.
  • Verify streamText implementations to ensure tool choices are being enforced as expected.
  • Note the changes in retry behavior for unclassified empty image results.

Keep Exploring

/studio?pack=foundation /techniques/output-schema /techniques/ptcf /techniques/system-user-separation /techniques/multimodal-grounding /techniques/constraints /techniques/role-objective /techniques/ask-before-inventing /techniques/multishot /techniques/xml-delimiting /techniques/direct-blocks-**grok**