Megatron MarketsWholesale
Sign inContact Us
Models Model details

Z.ai

Z.ai: GLM 4.5

z-ai/glm-4.5

Enquire about this model Request a quote

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 enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs

Input
$0.6

/ 1M tokens

Output
$2.2

/ 1M tokens

Context window
131.07K

tokens

Limits

Context

131,072

tokens

Max output

98,304

75% of the context window

Parameters

358,337,791,296

Model facts

Author

Z.ai

Tokenizer

Other

Modality

Text -> Text

License

MIT

Knowledge cutoff

2024-12-31

Created

Jul 25, 2025

Hugging Face

zai-org/GLM-4.5

Default generation parameters

temperature

0.75

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextOutput · Text

Generation controls

Include reasoningMax tokensReasoningResponse formatTemperatureTool choiceToolsTop kTop p

Capability scores

12.8
Intelligence index

Better than 32% of models compared

Creative tasks

Category performance

3D
Top 52%

1171 Elo

59.7% win

UI components
Top 66%

1143 Elo

55.0% win

Code
Top 63%

1167 Elo

54.4% win

Games
Top 60%

1146 Elo

54.4% win

Websites
Top 63%

1171 Elo

53.7% win

Data visualization
Top 67%

1160 Elo

53.3% win

SVG
Top 76%

1094 Elo

50.8% win