Zhipu AI: GLM-4.5-Air

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Model lab: Zhipu AI
Model family: glm-air

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output98,304

InputUSD 0.104 / 1M tokens

OutputUSD 0.68 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to zhipuai/glm-4.5-air.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "zhipuai/glm-4.5-air"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

GLM-4.5-Air API Pricing

Type	Price information
Input	USD 0.104 / 1M tokens
Output	USD 0.68 / 1M tokens

Benchmarks

Intelligence Index · v4.311.1

Coding Index—

Agentic Index—

Benchmark	Score	Measurement
Artificial Analysis Coding Index	23.8	index · Date: 2026-05-30
SciCode	30.6	percent correct · Date: 2026-05-30
Terminal-Bench Hard	20.5	success rate · Date: 2026-05-30

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Artificial Analysis measurement

Output speed76.4 tokens/s

Time to first token2.41 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput76.4 tok/sCurrent

Time to first token2.41 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current76.4 tok/s

Window average77.2 tok/s

Time to first token

Current2.41 s

Window average2.5 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current16.1 s

Window average16.3 s

Prompt cache hit rate

Current18.2%

Window average24.6%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

GLM-4.5-Air Compare models

Model	Input price	Output price	Context window	Capabilities
GLM-4.5-AirThis page	USD 0.104 / 1M tokens	USD 0.68 / 1M tokens	131,072	Text output · Reasoning · Tool calling
GLM-5.3	USD 0.0632 / 1M tokens · Quantization fp4	USD 1.12 / 1M tokens · Quantization fp4	1,000,000	Text output · Reasoning · Tool calling
GLM-5.2	USD 0.24 / 1M tokens	USD 0.84 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
GLM-5.1	USD 0.36 / 1M tokens	USD 1.72 / 1M tokens	200,000	Text output · Reasoning · Tool calling
GLM-5-Turbo	USD 0.96 / 1M tokens	USD 3.2 / 1M tokens	200,000	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 131,072
Maximum output: 98,304
Release date: 2025-07-28
Attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is GLM-4.5-Air for?

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

What inputs and outputs does GLM-4.5-Air support?

Recorded inputs: text; outputs: text.

How is GLM-4.5-Air priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.104 / 1M tokens; Output USD 0.68 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for GLM-4.5-Air?

Current model records list Context window 131,072 tokens; Maximum output 98,304 tokens.

What model parameter does the Quickstart use?

The example uses zhipuai/glm-4.5-air. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.