GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. Learn more in our docs

ChatZhipu66k tokens$0.654 / $1.9621 · 1M

z-ai/glm-4.5v

Context
66k tokens
Completion cap
16,384
Tools
Yes
JSON
Yes
Released
2025-08-11

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.5v",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is GLM 4.5V?
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses. Reasoning behavior can be toggled via the `reasoning` `enabled` boolean. Learn more in our docs GLM 4.5V runs on the Geek Hub API (OpenAI-compatible). Model id: z-ai/glm-4.5v.
Is GLM 4.5V free?
No. Input is $0.654 per 1M tokens and output is $1.9621 per 1M tokens on Geek Hub (markup included).
What is the context length of GLM 4.5V?
GLM 4.5V has a 66k tokens context window. It supports up to 16,384 completion tokens.
Does GLM 4.5V support tool calling and structured outputs?
GLM 4.5V accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GLM 4.5V released?
GLM 4.5V was released on 2025-08-11.

More models from Zhipu