GLM-4.6

Zhipu AIMCP Tool CallReasoning

zhipuai/glm-4.6Open Weights

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

Benchmark Pricing$0.60 / 1M in$2.20 / 1M out$0.11 cache read

Context: 204,800 tokens•Max Output: 131,072 tokens•Knowledge: 2025-04•Released: 2025-09-30

TECHNICAL SPECIFICATIONS

Context Window204,800204.8K tokens

Max Output131,072131.1K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GLM-4.6 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 204,800 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

Artificial Analysis Coding Indexindex

29.5

SciCodepercent correct

38.4

Terminal-Bench Hardsuccess rate

SWE-Bench Proresolve rate

9.67

API CALL INVOCATION EXAMPLE

// Example: Calling GLM-4.6 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-4.6",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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