Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
LLM Gateway logo

Model details

GLM-4.5 Air (Z AI)

GLM-4.5 Air is a text-to-text language model attributed to Z AI, designed as a lighter-tier variant within the broader GLM family. Third-party aggregator listings position it as an accessible alternative to heavier multimodal or reasoning-focused siblings, emphasizing a favorable balance between capability and operational cost. The model participates in independent leaderboard rankings alongside notable peers, indicating its relevance as a general-purpose conversational and reasoning engine rather than a narrow specialist.

In comparative evaluations against other Z AI offerings, GLM-4.5 Air is highlighted for delivering competitive reasoning scores at a notably lower input token price, with aggregator data reporting $0.17 per million input tokens and a blended value index that outpaces costlier variants. It also demonstrates faster token throughput than reasoning-heavy alternatives, making it well-suited for high-volume applications such as batch processing, agent pipelines, and developer-facing APIs where latency and budget matter more than maximum reasoning depth.

LLM Gatewayzai/glm-4.5-airglm-air

Quick Info

Powered by
Provider
LLM Gateway
Model key
zai/glm-4.5-air
Release date
Jul 28, 2025
Last updated
Jul 28, 2025
Knowledge cutoff
2025-04
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.20
Output token cost
$1.10

Limits

Output tokens
98,304 tokens
Context window
128,000 tokens

Transparent token rates

Compare GLM-4.5 Air (Z AI) pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GLM-4.5 Air (Z AI)

LLM Gateway

CoverageBenchmark

The Requesty model catalog page for GLM-4.5-Air confirms the model as part of Z.AI's GLM-4.5 series, an open-weight foundation model family designed for intelligent agents. The Air variant is described as a compact MoE design with 106 billion total parameters and 12 billion active parameters, unifying reasoning, coding Requesty reports a 131K-token context window with 4K maximum output for GLM-4.5-Air and lists one endpoint, DeepInfra Inc., pricing it at $0.20 per 1M input tokens, $1.10 per 1M output tokens, and $0.20 per 1M cached input tokens, with ZDR privacy available. The page also surfaces Artificial Analysis benchmark scores t

Videos about GLM-4.5 Air (Z AI)

More models around GLM-4.5 Air (Z AI)