ToolsThe story, in brief

GLM-5 is live on AI Gateway

GLM-5 just shipped to Vercel's AI Gateway. Agentic coding and autonomous tool use out of the box.

Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
New tools for building and creating with AI.AI illustration by KeyNews
The KeyNews take

Why it matters

GLM-5 availability through AI Gateway lowers friction for developers building agent-heavy applications. The model's emphasis on multi-step reasoning, long-range planning, and tool use signals competitive pressure in the reasoning/agent capability space—and distribution through a popular developer platform accelerates adoption.

The key facts

12 to know
  1. GLM-5 now available via Vercel AI Gateway

  2. Improvements over GLM-4.7: multiple thinking modes, improved long-range planning and memory

  3. Positioned for agentic coding, autonomous tool use, structured data extraction

  4. AI Gateway provides unified API, usage tracking, observability, intelligent provider routing

  5. No separate provider account required for access

  6. GLM-5 adds multiple thinking modes vs GLM-4.7

  7. Improved long-range planning and memory capabilities

  8. Strong on agentic coding and autonomous tool use

  9. Available via Vercel AI Gateway with unified API

  10. No additional provider accounts required

  11. Built-in observability and Bring Your Own Key support

  12. Intelligent provider routing with automatic retries

Go to the source

Vercel Blogvercel.com

Publisher excerpt: You can now access GLM-5 via with no other provider accounts required.AI Gateway GLM-5 from Z.AI is now available on AI Gateway. Compared to GLM-4.7, GLM-5 adds multiple thinking modes, improved long-range planning and memory, and better handling of complex multi-step agent tasks. It's particularly…
Read original report
Back to today's editionMore tools news

The wider picture

View all
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools01

Meta’s Muse is creepy, but maybe not for the reasons you think

A widely-deployed AI assistant shipped with a privacy and transparency gap that raises questions about how these tools actually work and what access they grant themselves. Practitioners need to understand what they're actually allowing when they install agent-adjacent products.

The Verge AI
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Tools02

TypeSafe AI Releases Jev: A System One Model That Returns Typed, Calibrated Decisions Instead of Text

A new class of models optimized for typed, probabilistic decisions rather than text generation—reshaping cost structure and reliability for classification, scoring, and decision-automation workflows. Changes how teams think about model selection for deterministic tasks.

MarkTechPost
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Tools03

Unity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorials

Unity is shipping official integrations that let frontier models access up-to-date documentation in real time, solving a real problem for developers using AI coding assistants: stale training data and outdated API references.

The Decoder