GLM 5

LLM
Z.AI

GLM 5 is a flagship reasoning model from Z.AI excelling at complex reasoning, multilingual programming, and agentic workflows with interleaved thinking, 200K context, and improved tool collaboration.

Context tokens

203,000

Output tokens

16,384

Released

Mar 7, 2026

Schema

OpenAI-compatible chat format via Google Vertex AI MaaS. GLM 5 uses a GLM-4-compatible schema; see the documentation URL.

Schema documentation

Capabilities

Thinking
Multilingual

Supported languages

en
zh

Supported tools

  • Seclai Web Tools

    Fetch web pages and search the web from within agent prompt calls. Includes seclai_web_fetch for retrieving page content in markdown, HTML, or plain text, and seclai_web_search for finding relevant pages with content snippets.

Pricing

TypeCreditsUnits
Input13.30Credits per 1k tokens
Output42.56Credits per 1k tokens
Cache hit1.33Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with GLM 5 in the model experiments page. You can compare it with other models side by side.