Z.ai: GLM 4.5

z-ai/glm-4.5

Tool useJSONReasoningStreaming

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Pricing

Input

$0.6 / 1M

Output

$2.20 / 1M

Specs

Context

131,072 tokens

Input

text

Output

text

Knowledge cutoff: 2024-12-31

Released: 2025-07

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

138,040 downloads/mo

1,402 likes

mit text-generation

arXiv:2508.06471

View on HuggingFace →

Use this model →