Zhipu AI’s GLM-4.5-Air is a highly efficient, cost-effective large language model built with 106 billion total parameters (12 billion active) using a Mixture-of-Experts (MoE) design. Tailored for a broad spectrum of text-to-text applications, it matches the full GLM-4.5’s 128,000-token context window, enabling comprehension and generation of very long-form text while dramatically reducing computational overhead.
GLM-4.5-Air is engineered for agentic applications, offering a 128,000-token context window and built-in function execution capabilities. On agentic benchmarks such as τ-bench and BFCL-v3, it attains results nearly equivalent to Claude 4 Sonnet. In specialized tests for web browsing (BrowseComp), which assess complex multi-step reasoning and tool use, GLM-4.5-Air achieves a 26.4% accuracy rate, outperforming Claude-4-Opus (18.8%) and approaching the leading o4-mini-high at 28.3%. These results underscore GLM-4.5-Air’s balanced performance in real-world, tool-driven tasks and agent scenarios.
Vs. Claude 4 Sonnet: GLM-4.5-Air offers a competitive balance of efficiency and performance but is slightly behind Claude 4 Sonnet in coding and agentic reasoning tasks. Claude 4 Sonnet supports a larger context window (200k tokens vs. 128k) and includes image input capabilities, making it more suitable for multimodal applications. However, GLM-4.5-Air is open-source, more cost-effective, and provides strong reliability across function calling and multi-turn reasoning.
Vs. GLM-4.5: GLM-4.5-Air achieves about 80-98% of the flagship GLM-4.5’s performance, with significantly fewer active parameters (12B vs. 32B) and reduced resource requirements. While it slightly trails in raw task accuracy, it maintains solid reasoning, coding, and agentic capabilities, making it better suited for deployment in hardware-constrained environments.
Vs. Qwen3-Coder: GLM-4.5-Air competes well with Qwen3-Coder in coding and tool use, delivering fast and accurate code generation for complex programming tasks. GLM-4.5-Air demonstrates dominant success rates and reliable tool calling mechanisms over Qwen3-Coder.
Vs. Gemini 2.5 Pro: GLM-4.5-Air holds close on practical reasoning and coding benchmarks against Gemini 2.5 Pro. While Gemini may excel slightly in some coding and reasoning tests, GLM-4.5-Air offers a favorable balance of large context window and agentic tooling optimized for efficient real-world deployments.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "zhipu/glm-4.5-air", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "zhipu/glm-4.5-air", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"zhipu/glm-4.5-air","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU-Pro | 81.4% | Multi-discipline knowledge + reasoning (harder MMLU) | Source | July 8, 2026 |
| Terminal-Bench | 30% | Autonomous shell/terminal task completion | Source | July 8, 2026 |
| SWE-bench Verified | 57.6% | Resolving verified real GitHub issues | Source | July 8, 2026 |
| Intelligence | 11.1 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Math | 80.7 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GLM-4.5 Air This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
GLM-4.5 Air has a 128,000 tokens context window and can return up to 98,000 tokens.
GLM-4.5 Air takes text as input and returns text.
Use zhipu/glm-4.5-air as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
GLM-4.5 Air became available on September 9, 2025.
GLM-4.5 Air is priced at input $0.26 / 1M tokens, output $1.43 / 1M tokens, cached input $0.039 / 1M tokens.
Yes, GLM-4.5 Air can stream responses as they are generated.
GLM-4.5 Air was built by Zhipu AI.
Yes, it supports function calling, parallel tool calls, and structured output as part of its tool use capabilities.
