GLM 4.6V

GLM-4.6V is Zhipu AI's vision-language model in the GLM-4 series, supporting image, document, video-frame, and chart understanding alongside text reasoning. It accepts long context, handles OCR-style document parsing, and is competitive with leading open multimodal models. Use it for visual question answering, document understanding pipelines, screenshot analysis, and multimodal agents.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="zhipu/glm-4.6v",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)