Languagetext

GLM 5.2

GLM-5.2 is Zhipu AI's (brand Z.AI) coding-focused flagship, launched June 13, 2026, a 744B-parameter mixture-of-experts model with about 40B active parameters per token. Its headline feature is a 1,000,000-token context window, a 5x jump over GLM-5.1, with maximum output around 131K tokens, suited to repo-scale diffs and long plan-then-execute traces. It ships with broad agent-tool compatibility (Claude Code, Cline, OpenClaw and others) and MIT-licensed open weights. Ideal for long-horizon coding and agentic engineering over very large codebases.

Entrada

Top p
01
Reasoning
Temperature
02
Max completion tokens
1200000
Ready to generateReady to generate

Referencia de la API

POSThttps://api.token360.ai/v1/chat/completions
curl https://api.token360.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "glm-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "temperature": 0.7,
  "top_p": 1,
  "max_completion_tokens": 4096
}'