Models/Z.ai/GLM 4.5 Air

GLM 4.5 Air

Name: GLM 4.5 Air API access
Brand: Z.ai

Z.ai · Open weights · Released Jul 25, 2025 · z-ai/glm-4.5-air

Compare Estimate cost

131K contextToolsReasoningPrompt cachingOpen weights

Available from 3 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Novita	$0.13	$0.85	$0.025	131K	bf16	1.8s	4 tok/s	99.3%
SiliconFlow	$0.14	$0.86	—	131K	fp8	2.6s	50 tok/s	85.0%
Z.AI1ST PARTY	$0.20	$1.10	$0.03	131K	fp8	1.8s	78 tok/s	99.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago

Pricing variants · USD / MTok in / out

STANDARD

$0.13 / $0.85

per MTok in / out

CACHE READ $0.025

About

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

Specifications

Context window131,072

Max output98,304

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedJul 25, 2025

Knowledge cutoff2024-12-31

TokenizerOther

WeightsHugging Face ↗

Open weights

Hugging Facezai-org/GLM-4.5-Air ↗

Downloads153.1K

Likes636

Licensemit

safetensors

GLM 5.3$1.40 / $4.40 GLM 5.2$0.50 / $2.00 GLM 5.1$0.91 / $2.86 GLM 5V Turbo$1.20 / $4.00

Embed badge

[![GLM 4.5 Air](https://modelindex.ai/badge/z-ai/glm-4.5-air)](https://modelindex.ai/models/z-ai/glm-4.5-air)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

Hugging Face4 minutes ago

COMMUNITY

ModelIndex benchmarks43 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.