ModelBench
Zhipu AI logo
Models/Zhipu AI

GLM-4.5-Air

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

Source-linked glm-air Open weights Released 2025-07-28
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.2/1M tokens
Output price$1.1/1M tokens
Context window131.072K
Max output98.304K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Creator
Zhipu AI
Model family
glm-air
Knowledge cutoff
2025-04
License
Not documented
Release date
2025-07-28
Model ID
zhipuai/glm-4.5-air
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering GLM-4.5-Air
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Z.AI Coding Plan glm-4.5-air 131.072K Not listed Not listed - ReasoningTools Docs
Zhipu AI Coding Plan glm-4.5-air 131.072K Not listed Not listed - ReasoningTools Docs
Hugging Face zai-org/GLM-4.5-Air 131.072K $0.13 $0.85 - ReasoningTools Docs
LLM Gateway glm-4.5-air 131K $0.13 $0.85 $0.025 ReasoningTools Docs
OpenRouter z-ai/glm-4.5-air 131.072K $0.13 $0.85 $0.025 ReasoningTools Docs
Zhipu AI glm-4.5-air 131.072K $0.2 $1.1 $0.03 ReasoningTools Docs
Merge Gateway zai/glm-4.5-air 131.072K $0.2 $1.1 $0.03 ReasoningTools Docs
OrcaRouter z-ai/glm-4.5-air 131.072K $0.2 $1.1 $0.03 ReasoningTools Docs
Z.AI glm-4.5-air 131.072K $0.2 $1.1 $0.03 ReasoningTools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Artificial Analysis Coding Index - Unversioned - indexTop 8 reported models
GPT-5-Codex
38.9
Step 3.7 Flash
37.1
Step 3.5 Flash 2603
34.6
Gemini 2.5 Pro
32.0
Step 3.5 Flash
31.6
GLM-4.6
29.5
Qwen3 Max
26.4
GLM-4.5-Air
23.8
SciCode - Unversioned - percent correctTop 8 reported models
Gemini 2.5 Pro
42.8
GPT-5-Codex
40.9
Step 3.5 Flash
40.4
Step 3.7 Flash
40.0
Gemini 2.5 Flash
39.4
Step 3.5 Flash 2603
38.5
GLM-4.6
38.4
GLM-4.5-Air
30.6
Terminal-Bench Hard - Unversioned - success rateTop 8 reported models
GPT-5-Codex
37.9
Step 3.7 Flash
35.6
Step 3.5 Flash 2603
32.6
Step 3.5 Flash
27.3
Gemini 2.5 Pro
26.5
GLM-4.6
25.0
GLM-4.5
22.0
GLM-4.5-Air
20.5
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/zhipuai/glm-4.5-air
curl
curl "https://www.modelbench.lol/api/v1/models/zhipuai/glm-4.5-air"