Sign in
← AI PulseAug 30, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates Image Generation Cost Summation and Anthropic Provider Metadata

The Vercel AI SDK, including packages like @ai-sdk/zai@3.0.3, @ai-sdk/xai@4.0.50, @ai-sdk/svelte@5.0.85, and @ai-sdk/togetherai@3.0.42, received updates to how image generation costs are summed and how Anthropic provider metadata is handled.

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/zai@3.0.3: Version Packages (#19931) · vercel/ai
Save

Vercel has released updates to its AI SDK, affecting multiple packages including @ai-sdk/zai@3.0.3, @ai-sdk/xai@4.0.50, @ai-sdk/svelte@5.0.85, and @ai-sdk/togetherai@3.0.42. These updates, part of the ai@7.0.85 release, address image generation cost calculations and Anthropic provider functionalities.

Key Points

  • The ai@7.0.85 release includes patch changes for several @ai-sdk packages.
  • A fix ensures that canonical hashes preserve undefined array element positions.
  • The SDK now correctly sums Gateway image-generation costs across split requests.
  • The Anthropic provider has been updated to preserve native message batch request counts in provider metadata.
  • The Anthropic provider also supports the full language-model option surface in batch requests.
  • Individual image generation calls are now exposed through the ai package.
  • Amazon Bedrock integration now enables Anthropic reasoning budgets for application inference profile ARNs.

Context

According to the Vercel AI SDK changelog, these updates were released via a Changesets release GitHub action. The changes aim to refine existing functionalities and introduce new capabilities within the SDK's various components and provider integrations.

Why It Matters

These updates improve the accuracy of cost tracking for image generation and enhance the flexibility of Anthropic model interactions for developers using the Vercel AI SDK. The addition of reasoning budgets for Anthropic models via Amazon Bedrock offers more granular control over resource usage.

What To Do

  • Review the ai@7.0.85 patch changes for specific impacts on existing implementations.
  • Test image generation cost calculations, especially for split requests, to confirm accurate summation.
  • Note the enhanced Anthropic provider metadata and language-model option support for batch requests.
  • Explore the exposure of individual image generation calls for new integration possibilities.
  • If using Amazon Bedrock, investigate the new Anthropic reasoning budget feature for application inference profile ARNs.