Inference
EN
Z.AI

GLM-4.5-Air

GLM-4.5-Air is a standard model from Z.AI. It has 7 scored results in 4 categories. It has no index.

  • Open weights
  • Standard
  • Input: text
  • Released 2025-07
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.55%
SpeedOutput tokens per second.64/sMedian 67/s
First tokenSeconds to the first output token.0.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.20Median $0.60
Output / 1MUS dollars per 1M output tokens.$1.10Median $2.55
ContextMaximum tokens in one request.131KMedian 262K
EloLMArena rating and rank.1384±4 #176Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
z-ai/glm-4.5-air
Max outputMaximum output tokens per request.
98K
Knowledge cutoffLast date of training data.
31 Dec 2024
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
No
Cache read / 1MUS dollars per 1M cached tokens.
$0.03
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
5 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
Novita AIHost$0.13$0.85131K
SiliconFlowHost$0.14$0.86131K
Zhipu AIMaker$0.12$0.896131K
OpenRouterRouter$0.20$1.10131K
Z.AIMaker$0.20$1.10131K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted33.6—
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.2 counted38.1—
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.3 counted35.7—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted24.2—
MathMath problems.None counted——

Results

7 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Artificial Analysis GPQA DiamondKnowledge73.3%126 / 199
τ²-Bench Tool-Agent-User EvaluationAgentic46.5%100 / 149
Critical Physics TasksReasoning0.0%150 / 214
Artificial Analysis Humanity's Last ExamKnowledge7.0%161 / 222
Artificial Analysis Long Context ReasoningReasoning46.7%162 / 217
Artificial Analysis IFBenchInstruction37.6%116 / 146
Artificial Analysis Omniscience AccuracyKnowledge16.3%147 / 164

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reusemodels.devMIT

History

5 releases
Output / 1M$0.85 → $1.10
23 Oct 202612 Nov 2026

Questions

How much does GLM-4.5-Air cost?
$0.20 per 1M input tokens, $1.10 per 1M output tokens.
How fast is GLM-4.5-Air?
64 output tokens per second, 0.6 s to the first token.
What is the context window of GLM-4.5-Air?
131K tokens.
Is GLM-4.5-Air open source?
Yes. Its weights are published.
When was GLM-4.5-Air released?
July 2025.

More from Z.AI

All models
GLM-4.545.7GLM 4.5VUnrankedGLM-4.641.8GLM 4.6VUnrankedGLM-4.750.0