GLM 4.5 Air

by Z.ai · Released · Announcement · All Z.ai releases

GLM 4.5 Air is the efficiency-focused variant of the GLM-4.5 series, with 106 billion total parameters and only 12 billion active per forward pass through MoE routing. Designed to run on consumer-class GPUs and quantizable for broader hardware, it reports a benchmark score of 59.8, leading models in its parameter tier while keeping compute requirements modest. The model keeps the hybrid reasoning design of its larger sibling, switching between a thinking mode for complex tasks and a non-thinking mode for immediate responses. Its 128K context window and strong tool-calling results make it a fit for resource-constrained agentic systems where speed and cost matter alongside capability. Training spans many languages with strong Chinese and English fluency, and it ships under an MIT license for commercial use and further development. GLM 4.5 Air is aimed at agent applications that need a balance of reasoning depth and inference efficiency, including local deployment and cost-sensitive production systems where a smaller active parameter count reduces latency.

Sign up without a credit card · OpenAI SDK compatible
Input
$0.13 / 1M
Output
$0.85 / 1M
Cache read
$0.02 / 1M
Context
131K tokens
Max output
131K tokens
Routes
2 EU · US

Available routes

GLM 4.5 Air runs on 2 different routes through the Opper gateway.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$0.14$0.86$0.02
USNo$0.13$0.85$0.03

Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by FlexAI. See every GLM model hosted in the EU.

Live routes and prices as JSON: api.opper.ai/v3/models?q=glm-4.5-air

Key info

Input
Output
Features
Context window
131K
Max output
131K
Input price
$0.14 /1M$0.02 cache read
Output price
$0.86 /1M
Released
Web search
  • EU residency available on FlexAI
  • US residency available on Novita
  • Zero data retention on pay-as-you-go
  • No training by default

Uptime and availability

One of GLM 4.5 Air's 2 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

100%route uptime, last 30 days
Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route is not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting GLM 4.5 Air has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

FlexAI — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
No classifier
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
Transfer mechanism
Not applicable — data stays in EU

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
On by default, keeps nothing
Transfer mechanism
SCCs

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#261 of 519 LLMs
TierEfficient
Output speed76 tok/s
Intelligence Index (previous version)11.1
Coding
LiveCodeBench
68%
Agentic & knowledge work
Terminal-Bench Hard
21%
τ²-Bench Telecom
47%
Science & reasoning
Humanity's Last Exam
7%
GPQA Diamond
73%
Long-context reasoning
47%
Knowledge
MMLU-Pro
82%
Math & instruction following
AIME 2025
81%
IFBench
38%

Get started

Call GLM 4.5 Air through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

GLM 4.5 Air is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "glm-4.5-air",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Use GLM 4.5 Air in your apps

Pick your tool, then choose GLM 4.5 Air to see how to run it through Opper.

Use GLM 4.5 Air with tools

The tools GLM 4.5 Air can use through Opper. Pick one to see how to set it up.

Compare GLM 4.5 Air with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Z.ai

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation