Back to Models

GLM 4.5 Air

GLM-4.5 Air is an efficient MoE model with 106B parameters (12B active). It is optimized for agentic applications, tool use, and speed.

Thinking Mode
Parameters
106000000000 B
Context
128,000 tokens
Released
Invalid Date

Leaderboards

Performance vs. Industry Average

Intelligence

GLM 4.5 Air is of lower intelligence compared to average (4.1), with an intelligence score of 3.9.

Price

GLM 4.5 Air is cheaper compared to average ($4.58 per 1M Tokens) with a price of $0.54 per 1M Tokens.

Latency

GLM 4.5 Air has a higher average latency compared to average (116.45s), with an average latency of 163.15s.

P99 Latency

GLM 4.5 Air has a higher P99 latency compared to average (339.37s), taking 425.28s to receive the first token at P99 (TTFT).

Context Window

GLM 4.5 Air has a smaller context window than average (351k tokens), with a context window of 128k tokens.

GLM 4.5 Air - AutoBench