GLM-4.6

面向编码、长上下文任务、推理、搜索和智能体任务的文本模型，上下文 200K。

Zhipu AIglm-4.62025-09-30报告数据错误

规格

上下文: 202.8K
最大输出: 131.1K
输入价: $0.6/ 百万 Token
输出价: $2.2/ 百万 Token
发布日期: 2025-09-30

上下文

上下文: 202.8K
最大输入: —
最大输出: 131.1K

价格 · USD / 百万 Token

输入: $0.6
输出: $2.2
缓存读取: $0.11
缓存写入: —

输入输出

输入: 文本
输出: 文本

API

接口类型: chat

思考

支持思考: 支持
思考等级: —

源信息

状态: 可用
发布日期: 2025-09-30
知识截止: —

能力

已确认: toolsstructured_outputstreamingcaching

调用方式

zhipumodel = glm-4.6reasoning = thinking.type

chat

POSThttps://api.z.ai/api/paas/v4/chat/completions

JSON

glm-4.6.json

{
  "id": "glm-4.6",
  "object": "model",
  "created": 1759190400,
  "owned_by": "zhipu",
  "name": "GLM-4.6",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": 202752,
    "input": null,
    "output": 131072
  },
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 0.6,
    "output": 2.2,
    "cache_read": 0.11,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching"
  ],
  "info": {
    "status": "active",
    "release_date": "2025-09-30",
    "knowledge_cutoff": null,
    "description": "Text model for coding, long-context work, reasoning, search and agentic tasks with 200K context.",
    "docs": "https://docs.z.ai/guides/llm/glm-4.6",
    "verified_at": "2026-10-10"
  }
}

官方来源

GLM-4.6 | Z.AI Developer Documentdocs.z.ai2026-10-10 Pricing | Z.AI Developer Documentdocs.z.ai2026-10-10 Release Notes | Z.AI Developer Documentdocs.z.ai2026-10-10 Create Chat Completion (max_tokens maximum 131072) | Z.AI Developer Documentdocs.z.ai2026-10-10 GLM-4.6 config.json (max_position_embeddings 202752) | Hugging Facehuggingface.co2026-10-10