Zhipu: glm-4.5-air

glm-4.5-air
131.1K context96K outReasoningToolsCache
Released Jul 25, 2025Knowledge cutoff 2024Updated Jul 25, 2025

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

Mode chatTokenizer OtherQuantization fp8zai-org/GLM-4.5-Air

All providers for this model are busy right now

Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.

Request this model on Discord

Pricing

Input price
$0.07/ 1M tokens$0.2066% off
Output price
$0.38/ 1M tokens$1.1066% off
Context window 131.1K tokensCompatible endpoints openaiVendor Zhipu

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltySome providersNot sent by default
include_reasoningAll providers-
max_tokensAll providers-
presence_penaltySome providers-
reasoningAll providers-
repetition_penaltySome providers-
seedSome providers-
stopSome providers-
temperatureAll providers0.75
tool_choiceAll providers-
toolsAll providers-
top_kAll providers-
top_pAll providersNot sent by default

Frequently asked questions

Similar models