← All models
Z

Z.ai: GLM 4.6

z-ai/glm-4.6

Tool useJSONReasoningStreaming

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

Pricing

Input

$0.43 / 1M

Output

$1.74 / 1M

Specs

Context

202,752 tokens

Input

text

Output

text

Knowledge cutoff: 2025-03-31

Released: 2025-09

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

40,267 downloads/mo
1,223 likes
mit text-generation
View on HuggingFace →