← AI PulseAug 21, 2026

Wire · news · Multi-source brief

Vercel AI SDK Updates DeepSeek V4 Flash Vision Exp and Video Webhook Support

Vercel's AI SDK has been updated to include support for DeepSeek V4 Flash Vision Exp image input and Files API, alongside webhook functionality for video model generation.

By Illumora Editorial

Source · Aug 21, 2026, 3:45 PM · On Illumora · Aug 21, 2026, 3:58 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/tui@1.0.75 · vercel/ai
Save

The Vercel AI SDK has received updates across several packages, including @ai-sdk/tui@1.0.75, @ai-sdk/workflow@2.0.4, @ai-sdk/vue@4.0.74, and @ai-sdk/workflow-harness@1.0.82. These updates introduce new features for image input, file handling, and video model interactions.

Key Points

  • The @ai-sdk/deepseek@3.0.30 package now supports DeepSeek V4 Flash Vision Exp image input.
  • The @ai-sdk/deepseek@3.0.30 package also includes Files API support.
  • The @ai-sdk/gateway@4.0.60 package implements handleWebhookOption for the video model.
  • This implementation allows generateVideo({ webhook }) to register a factory URL as the gateway's callbackUrl.
  • The webhook mechanism enables awaiting delivery instead of falling back to polling for video generation.
  • The ai package was updated to version 7.0.74.

Context

According to the Vercel AI SDK Changelog, these updates were released through the Changesets release GitHub action. The changes affect multiple packages within the SDK, indicating a broader set of enhancements across the platform.

Why It Matters

These updates expand the capabilities of the Vercel AI SDK for developers working with multimodal models and asynchronous operations. The addition of DeepSeek V4 Flash Vision Exp support provides new options for image processing, while the webhook implementation for video generation can streamline workflows by enabling push notifications for completion rather than continuous polling.

What To Do

  • Review the updated documentation for @ai-sdk/deepseek to understand the new DeepSeek V4 Flash Vision Exp image input and Files API capabilities.
  • Investigate the handleWebhookOption in @ai-sdk/gateway if developing applications that generate video.
  • Test the generateVideo({ webhook }) functionality to observe the change from polling to webhook delivery.
  • Note the updated ai package version 7.0.74 for dependency management.