GLM-4.6V-Flash

GLM-4.6V-Flash is a lightweight vision model from Z.ai for visual reasoning, documents, and multimodal agents. It is part of the glm-flash line, succeeding GLM-4.5-Flash. It has a 128000-token context window and a 32768-token output limit. Weights are open. It supports reasoning mode and tool calling. It accepts image, text, and video inputs and returns text. Pricing starts at $0.0218 per million input tokens and $0.2184 per million output tokens, with cached input at $0.0044 per million tokens. It is served by 5 hosts.

Against GLM-4.5-Flash: window 131K to 128K, input $0.00 to $0.0218, output $0.00 to $0.2184, cached input $0.00 to $0.0044.

Range across the hosts that serve it: up to $0.30 per 1M input tokens.

• ·Visual reasoning on images, text, and video
• ·Document understanding for multimodal tasks
• ·Supports reasoning mode and tool calling
• ·Open weights for self-hosting
• ·128k context window with 32k output

• Reach for it for visual reasoning on images and video
• Reach for it for document analysis and extraction
• Reach for it for building multimodal agents
• Reach for it for tasks needing tool calling and reasoning

5 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 and output limit?

The context window is 128000 tokens and the maximum output is 32768 tokens.

Does it support video input?

Yes, it accepts image, text, and video inputs, and returns text.

Is the model open weights?

Yes, the weights are open. It also supports reasoning mode and tool calling.