GLM-5.3

Zhipu AIMCP Tool CallReasoning

zhipuai/glm-5.3Open Weights

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Benchmark Pricing$1.20 / 1M in$4.18 / 1M out$0.30 cache read

Context: 1,000,000 tokens•Max Output: 131,072 tokens•Released: 2026-08-14

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M 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-5.3 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 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

Terminal-Benchpass@1

88.2

Terminal-Benchavg@3

28.3

DeepSWEresolved

66.9

NL2Reposcore

ProgramBenchalmost solved

FrontierSWEdominance score

78.1

SWE-Marathonscore

42.5

PostTrainBenchweighted average

39.8

CyberGympass@1

84.5

ExploitGymtasks solved

105

ExploitGymtasks solved

130

ExploitBenchaverage coverage

54.4

Toolathlon-Verifiedpass@1

AutomationBenchpass@1

48.2

Agents' Last Examscore

28.5

Humanity's Last Examaccuracy

62.5

GDPval-AAElo

1769

API CALL INVOCATION EXAMPLE

// Example: Calling GLM-5.3 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-5.3",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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