zai

GLM 4.5 X

zai/glm-4.5-x

GLM 4.5 X pairs the massive knowledge base of GLM 4.5 with an ultra‑fast inference stack architected for throughput‑first applications. By exploiting expert routing, flash attention, and speculative decoding, it streams answers at up to twenty thousand tokens per second on contemporary A100 clusters, rivaling much smaller models in latency. Extensive tool‑use training lets it chain API calls, run code, and retrieve documents while keeping conversation fluid. Powerful reasoning ensures accurate analysis of financial models, legal contracts, and scientific papers in real time. Organizations with demanding SLAs choose GLM 4.5 X when both depth and speed are non‑negotiable.

Tools

Function Calling

Context Window

128,000

Max Output Tokens

96,000

Language

PythonJavaScriptCurl

Using GLM 4.5 X with Python API

Using GLM 4.5 X with OpenAI compatible API

import openai

client = openai.Client(
  api_key= '{your_api_key}',
  base_url="https://api.model.box/v1",
)
response = client.chat.completions.create(
model="zai/glm-4.5-x",
messages: [
  {
    role: 'user',
    content:
      'introduce your self',
    },
  ]
)
print(response)