GLM-4.5-Flash

Zhipu AIMCP Tool CallReasoning

zhipuai/glm-4.5-flashClosed API

Efficient GLM model for fast reasoning, coding, and agent workflows

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out$0.00 cache read

Context: 131,072 tokens•Max Output: 98,304 tokens•Knowledge: 2025-04•Released: 2025-07-28

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output98,30498.3K tokens

LicenseProprietaryCloud API only

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GLM-4.5-Flash natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling GLM-4.5-Flash via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ZHIPUAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "zhipuai/glm-4.5-flash",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);