← AI PulseAug 26, 2026

Wire · news · Multi-source brief

Vercel AI SDK Adds Z.AI Provider with GLM Chat Completions and Multimodal Inputs

The Vercel AI SDK now includes a Z.AI provider, offering GLM chat completions, streaming, reasoning, tools, and multimodal input capabilities, according to a recent release.

By Illumora Editorial

Source · Aug 26, 2026, 7:36 PM · On Illumora · Aug 26, 2026, 7:48 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/zai@3.0.1 · vercel/ai
Save

The Vercel AI SDK has integrated a new Z.AI provider, enabling GLM chat completions, streaming, reasoning, tools, and multimodal inputs. This update, released on August 26, also adds support for the GLM-5.3-Flash model within the Z.AI provider and AI Gateway.

Key Points

  • The Z.AI provider is now available in the Vercel AI SDK.
  • It supports GLM chat completions, streaming, reasoning, and tools.
  • Multimodal inputs are a feature of the new Z.AI provider.
  • The GLM-5.3-Flash model is supported by the Z.AI provider and AI Gateway.
  • The release occurred on August 26.

Context

According to Vercel, the integration of the Z.AI provider represents a major change to the AI SDK. This addition expands the range of models and capabilities available to developers using the SDK, particularly for tasks involving advanced chat functionalities and multimodal data processing.

Why It Matters

This update provides developers with new options for incorporating advanced AI capabilities into their applications, particularly those requiring GLM models, multimodal input processing, or specific tool-use functionalities. The inclusion of GLM-5.3-Flash expands the performance choices available.

What To Do

  • Review the Vercel AI SDK documentation for details on the Z.AI provider.
  • Test the GLM chat completions, streaming, and reasoning features.
  • Experiment with multimodal inputs using the new provider.
  • Note the support for the GLM-5.3-Flash model in Z.AI and AI Gateway.

Keep Exploring

/atlas/llama-open