ModelInfo
English
All models

GLM-4.5-X

High-performance GLM-4.5 variant with strong reasoning and ultra-fast response.

Zhipu AIglm-4.5-xReport incorrect data

Specs

Context
—
Max output
—
Input price
$2.2/ 1M tokens
Output price
$8.9/ 1M tokens
Released
—

Context

Not published

Pricing · USD / 1M tokens

Input
$2.2
Output
$8.9
Cache read
$0.45
Cache write
—

Modalities

Input
Text
Output
Text

API

API types
chat

Reasoning

Reasoning
Yes
Levels
—

Info

Status
Deprecated
Released
—
Knowledge cutoff
—

Features

Confirmed
toolsstructured_outputstreamingcaching
Source · official docsVerified 2026-10-11

How to call

1 provider

zhipumodel = glm-4.5-xreasoning = thinking.type

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

JSON

Standard format
glm-4.5-x.json
{
  "id": "glm-4.5-x",
  "object": "model",
  "created": null,
  "owned_by": "zhipu",
  "name": "GLM-4.5-X",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 2.2,
    "output": 8.9,
    "cache_read": 0.45,
    "cache_write": null
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching"
  ],
  "info": {
    "status": "deprecated",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "High-performance GLM-4.5 variant with strong reasoning and ultra-fast response.",
    "docs": "https://docs.z.ai/guides/llm/glm-4.5",
    "verified_at": "2026-10-11"
  }
}

Official sources

4