Sign in
← AI PulseAug 30, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates Include Anthropic Batch Request Support and Image Generation Cost Summing

The Vercel AI SDK has received updates, including enhanced support for Anthropic batch requests, improved image generation cost tracking, and the enablement of Anthropic reasoning budgets for Amazon Bedrock application inference profiles.

By Illumora Editorial

Source · Aug 30, 2026, 7:58 AM · On Illumora · Aug 30, 2026, 8:08 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/workflow-harness@1.0.94: Version Packages (#19931) · vercel/ai
Save

Vercel has released updates to its AI SDK, including @ai-sdk/workflow-harness@1.0.94, @ai-sdk/zai@3.0.3, @ai-sdk/xai@4.0.50, and @ai-sdk/workflow@2.0.15. These updates introduce several enhancements for developers working with AI models, particularly concerning Anthropic integrations and image generation functionalities.

Key Points

  • The Vercel AI SDK now preserves native message batch request counts in provider metadata for Anthropic.
  • The updates support the full language-model option surface in Anthropic batch requests.
  • The Gateway component of the AI SDK now sums image-generation costs across split requests.
  • Individual image generation calls are now exposed within the AI SDK.
  • Anthropic reasoning budgets have been enabled for application inference profile ARNs on Amazon Bedrock.
  • Canonical hashes ensure undefined array element positions are preserved.

Context

According to the Vercel AI SDK Changelog, these updates address specific technical improvements. The changes aim to refine how the SDK handles requests to Anthropic models, particularly for batch operations, and to provide more accurate cost tracking for image generation tasks. The enablement of Anthropic reasoning budgets on Amazon Bedrock indicates an effort to optimize resource usage for inference profiles.

Why It Matters

These updates offer developers more granular control and transparency when integrating Anthropic models and managing image generation costs within their applications. The improved cost tracking and enhanced Anthropic batch request capabilities can lead to more efficient and predictable resource utilization for builders.

What To Do

  • Review the updated Vercel AI SDK documentation for details on Anthropic batch request handling.
  • Test the new image generation cost summing feature to verify its accuracy for your applications.
  • Note the exposure of individual image generation calls for potential new monitoring or logging strategies.
  • If using Anthropic models on Amazon Bedrock, evaluate the impact of enabled reasoning budgets on application inference profiles.