glm-4.5

completions

byzai

glm-4.5

completions

Published by: z-aiProvider:

zai

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses.

Released

Jul 28, 2025

Knowledge

Jan 29, 2025

Context

131072

Input

$0.6 / 1M tokens

Output

$2.2 / 1M tokens

Cached

$0.11 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Jul 28, 2025Knowledge Cutoff: Jan 29, 2025

Context: 131072 Input: $0.6 / 1M tokensOutput: $2.2 / 1M tokensCached: $0.11 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access glm-4.5 through LangDB AI Gateway

Recommended

Integrate with z-ai's glm-4.5 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for glm-4.5

Category Performance Scores:

Academia: Score 63.80 (Top 11% - Rank #36)
Finance: Score 71.00 (Top 7% - Rank #23)
Marketing: Score 37.00 (Top 36% - Rank #117)
Maths: Score 92.60 (Top 7% - Rank #23)
Programming: Score 54.30 (Top 8% - Rank #26)
Science: Score 78.20 (Top 14% - Rank #46)
Writing: Score 30.36 (Top 35% - Rank #114)

Overall Performance: 61.037142857142854 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	87.30	Top 7%	Mathematics
AA Coding Index	54.30	Top 8%	Programming
AAII	49.40	Top 11%	General
AA Math Index	92.60	Top 7%	Mathematics
GPQA	78.20	Top 14%	STEM (Physics, Chemistry, Biology)
HLE	12.20	Top 10%	General Knowledge
LiveCodeBench	73.80	Top 6%	Programming
MATH-500	97.90	Top 6%	Mathematics
MMLU-Pro	83.50	Top 11%	General Knowledge
SciCode	34.80	Top 31%	Scientific

GPQA Score: 78.20 - Graduate-level reasoning benchmark

Model Comparison:

Provider: zai

Model Type: completions

Context Size: 131072 tokens

Comparing against 324 models in the database

Performance Analytics for glm-4.5

Usage Statistics (Last 8 Days):

Total Requests: 350 API calls
Average TPS: 436.24 tokens per second
Average Response Time: 14574.60ms
Average Time to First Token: 3898.80ms
Total Cost: $1.91
Average Request Cost: $0.0055

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/4/2025	28	463.10	12658.20ms	2426.70ms	$0.14
9/5/2025	21	594.89	12428.90ms	2072.80ms	$0.14
9/6/2025	97	293.37	16628.60ms	3941.50ms	$0.42
9/7/2025	31	519.39	13105.70ms	2144.60ms	$0.19
9/8/2025	15	575.24	12427.80ms	2045.20ms	$0.09
9/9/2025	55	270.86	22536.30ms	9624.80ms	$0.31
9/10/2025	78	705.14	10485.20ms	2437.30ms	$0.47
9/11/2025	25	907.29	8906.80ms	2166.00ms	$0.15

Performance Summary:

Model: glm-4.5 by zai

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 44

Peak Daily Requests: 97

Statistics

View Full Statistics

Request Volume

Daily API requests

350

Performance (TPS)

Tokens per second

436.24 tokens/s

Category Scores

academia#12 finance#7 maths#7 programming#9 science#17

Benchmark Tests

View Other Benchmarks

AIME

87.3

Mathematics

AA Coding Index

54.3

Programming

AAII

49.4

General

AA Math Index

92.6

Mathematics

GPQA

78.2

STEM (Physics, Chemistry, Biology)

HLE

12.2

General Knowledge

LiveCodeBench

73.8

Programming

MATH-500

97.9

Mathematics

MMLU-Pro

83.5

General Knowledge

SciCode

34.8

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	87.3	54.3	49.4	92.6	78.2	12.2	73.8	97.9	83.5	34.8

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for glm-4.5

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="glm-4.5",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "glm-4.5",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

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

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.5",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: glm-4.5

Provider: zai

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from zai

glm-4.5

glm-4.5

Access glm-4.5 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

glm-4-32b

glm-4.5-air

glm-4.5-airx

glm-4.5v

glm-4.5-x

glm-4.5 by zai - AI Model Details, Pricing, and Performance Metrics

glm-4.5

glm-4.5

Access glm-4.5 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

glm-4-32b

glm-4.5-air

glm-4.5-airx

glm-4.5v

glm-4.5-x