GLM-5V-Turbo

GLM-5V-Turbo is a fast vision model from Z.ai for screenshots, documents, and multimodal agent tasks. It is part of the GLM line, following GLM-5-Turbo. It has a 200,000 token context window and a 131,072 token output limit. Input starts at $0.7042 per million tokens, output at $3.10 per million, cached input at $0.169. Weights are not open. It supports image, PDF, text, and video inputs, returns text, and has reasoning and tool calling modes.

Against GLM-5-Turbo: input $0.72 to $0.7042, output $3.19 to $3.10, cached input $0.174 to $0.169.

Range across the hosts that serve it: up to $5.00 per 1M input tokens.

• ·Fast vision model for screenshots and documents
• ·200k token context window
• ·131k token max output
• ·Supports image, PDF, text, video input
• ·Reasoning mode and tool calling

• Reach for it for screenshot analysis and document understanding
• Reach for it for multimodal agent tasks
• Reach for it for video understanding
• Reach for it for long-context vision tasks

16 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window size?

200,000 tokens.

Can it process video?

Yes, it accepts video input and returns text.

Are the weights open?

No, the weights are not open.