GLM 4.5V

zai-org/glm-4.5v

Z.ai's GLM-4.5V sets a new standard in visual reasoning, achieving state-of-the-art performance across 42 benchmarks among open-source models. Beyond benchmarks, it excels in real-world applications through hybrid training, enabling comprehensive visual understanding—from image and video analysis and GUI interaction to complex document processing and precise visual grounding. In China's GeoGuessr challenge, GLM-4.5V outperformed 99% of 21,000 human players within 16 hours, reaching 66th place within a week. Built on the GLM-4.5-Air foundation and adopting the approach of GLM-4.1V-Thinking, it utilizes a 106-billion-parameter MoE architecture for scalable, efficient performance. This model bridges advanced AI research with practical deployment, delivering unmatched visual intelligence

Price

Input	$0.6 per million tokens
Output	$1.8 per million tokens

Use the following code example to integrate our API:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.jiekou.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="zai-org/glm-4.5v",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=16384,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

Information

Provider

ZhipuAI

Quantification

fp8

Supported Features

Context length

65536

Maximum output

16384

Function call

Support

Structured output

Support

Reasoning

Support

serverless

Support

Input Capabilities

text, image, video

Output Capabilities

text