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.
GLM 4.5 Air runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance β full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Enterprise | No | $0.13 | $0.85 |
Training posture across routes: No training on prompts by default.
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.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call GLM 4.5 Air through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent β Claude Code, Cursor, Codex, and more β and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.click/v3/compat",});const completion = await client.chat.completions.create({model: "novita/zai-org/glm-4.5-air",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
