Loading...
Loading...
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 size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
Quality Index
23.2
159th of 442
Top 36%
Coding Index
23.8
121st of 352
Top 34%
Math Index
80.7
61st of 268
Top 23%
Price/1M
$0.42
371st cheapest
37% above median
Top 55%
Speed
101 tok/s
Top 27%
TTFT
0.63s
Context Window
131K
145th largest
Top 63%
Input
$0.20
per 1M tokens
Output
$1.10
per 1M tokens
Blended
$0.42
per 1M tokens
Cheaper than 45% of models. Median price is $0.31/1M tokens.
Daily
$0.42
Monthly
$12.75
101
tokens/sec
Faster than 73% of models
0.63
seconds
Faster than 40% of models
20.36
seconds
Faster than 13% of models
Market Median
46 tok/s
122% faster
Median TTFT
0.42s
51% slower
Throughput/Dollar
239
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 37% of models
Max Output
98K
tokens
75% of context