Zhipu: glm-4.5v:free

glm-4.5v:free
64K context32K outReasoningToolsVisionCacheStructured
Released Aug 11, 2025Knowledge cutoff 2024Updated Aug 11, 2025

A flagship vision-language model based on GLM-4.5-Air (106B total/12B active). It specializes in "Thinking Mode" for complex visual reasoning, multi-page document parsing, and zero-shot GUI automation, matching Gemini 2.5 Pro performance.

Mode chatTokenizer OtherQuantization fp8zai-org/GLM-4.5V

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 128K 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-
response_formatAll 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