Sign in
← AI PulseAug 30, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates Image Generation Costs, Anthropic Batch Requests, and Bedrock Reasoning Budgets

Vercel has released updates to its AI SDK, including changes to how image generation costs are summed, enhanced support for Anthropic batch requests, and the enablement of Anthropic reasoning budgets for Amazon Bedrock.

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/tui@1.0.86 · vercel/ai
Save

Vercel has updated its AI SDK with several changes, as detailed in recent changelog entries. The @ai-sdk/tui@1.0.86 release, alongside other package updates, introduces modifications to image generation cost calculations and expands support for Anthropic's language model options in batch requests.

Key Points

  • The @ai-sdk/tui@1.0.86 release ensures canonical hashes preserve undefined array element positions.
  • The AI SDK now sums Gateway image-generation costs across split requests.
  • The Anthropic provider preserves native message batch request counts in provider metadata.
  • The Anthropic provider supports the full language-model option surface in batch requests.
  • Individual image generation calls are now exposed in the AI SDK.
  • Amazon Bedrock now enables Anthropic reasoning budgets for application inference profile ARNs.
  • The AI SDK exposes parsed structured output in streamText end callbacks, according to the @ai-sdk/tui@1.0.85 release.
  • Amazon Bedrock accepts citation deltas in streaming responses, as noted in the @ai-sdk/amazon-bedrock@5.0.67 release.

Context

According to Vercel's changelog, these updates include fixes and new features across various components of the AI SDK. The changes address how costs are managed for image generation and improve the integration with Anthropic's API for batch requests. Additionally, the Amazon Bedrock integration now supports specific Anthropic reasoning budgets.

Why It Matters

These updates provide developers with more precise cost tracking for image generation, broader control over Anthropic language model options in batch processing, and enhanced capabilities for managing reasoning budgets within Amazon Bedrock. These changes can impact the efficiency and cost-effectiveness of AI applications built with the Vercel AI SDK.

What To Do

  • Review the updated documentation for @ai-sdk/tui@1.0.86 to understand changes in canonical hash preservation.
  • Examine the AI SDK's image generation features to understand how costs are now summed across split requests.
  • Test Anthropic batch requests with the AI SDK to utilize the expanded language-model option surface.
  • Note the enablement of Anthropic reasoning budgets for Amazon Bedrock application inference profile ARNs.
  • Check the streamText end callbacks for newly exposed parsed structured output.
  • Observe how Amazon Bedrock streaming responses now handle citation deltas.