Z

Z.ai Model API

Model API

by Z.ai (Zhipu AI)

Hosted API for the GLM model family, billed per token.

Find alternatives to Z.ai Model API

Per-token rates and a contact-sales tier are stated on the product page itself. GLM is a model family and belongs in models.json.

What it does

• Code generation
• Text generation
• Video generation
• Image generation

How it compares

• K-EXAONE 2.0

  In global and Korean long-context comprehension benchmarks (OpenAI-MRCR and Ko-LongBench), the model scored 94.4 and 89.6, respectively, outperforming Zhipu's GLM-5.1.

  News reporting · 19 Sep 2026
• Solar LLMs

  84.4 on KorMedMCQA for medical domains (+3.9pp over GLM-4.5-Air, +8.6pp over gpt-oss-high)

  Research report · 19 Sep 2026

Sources

Pricing

Official documentation · 21 Aug 2026

Per-token rates and a contact-sales tier are stated on the product page itself. GLM is a model family and belongs in models.json.

Sold within

Pricing page · 6 Sep 2026

https://z.ai/usage-bundles - API access is bought directly, pay-per-token or as prepaid token bundles. No parent purchase is a precondition.

Interfaces

Official documentation · 28 Sep 2026

Nav links to an API Reference and Developer Docs for the Model API product.

Also from Z.ai (Zhipu AI)

• Z.ai Application

  Assistant built on the GLM models, covering chat, web search and document work.

• GLM Coding Plan Developer tool

  Flat-rate monthly subscription providing GLM model access inside third-party coding agents and IDEs such as Claude Code, Codex, Cline, OpenCode, Cursor and Windsurf, billed separately from Z.ai's per-token API.

• AutoClaw AI agent

  Locally installed AI agent application with 50+ preconfigured skills that performs document generation, data analysis, browser automation and messaging-app collaboration, running on Windows, macOS, iOS and Android and defaulting to the GLM-5.3 model.

• Zhipu Qingyan Application

  Zhipu's Chinese-market consumer AI assistant and agent built on the GLM model family, covering dialogue, writing, coding, translation and multimodal input.

• AutoGLM Application

  Deep-research assistant that searches and scrapes source websites to produce structured research reports and can emit the result as a slide deck or web page, with browser automation and video summarisation.

• AMiner Application

  AI research assistant built on Zhipu's GLM models that performs academic and scholar search, AI-assisted paper reading, literature-review generation with citations, and scholarly question answering.

Open Z.ai (Zhipu AI) in the directory

Something wrong here? Send a correction — quote this product id: z-ai-api.