cuuupid/glm-4v-9b

OfficialView on Replicate →

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image`*	string(uri)	Image input	`—`	—
`prompt`*	string	Prompt	`—`	—
`max_length`	integer	Maximum number of tokens to generate.	`512`	min: 1, max: 8192
`top_k`	integer	Top-K sampling	`1`	min: 1, max: 1000

imagerequiredstring

Image input

promptrequiredstring

Prompt

max_lengthinteger

Maximum number of tokens to generate.

Default: 512min: 1, max: 8192

top_kinteger

Top-K sampling

Default: 1min: 1, max: 1000

Version: 69196a237cdcUpdated: 7/25/202693.5K runs