GLM-5.1

GLM-5.1 is a coding model from Z.ai (Zhipu) for agentic engineering, terminals, and repository generation. It is part of the GLM line, released on 2026-04-07, following GLM-5V-Turbo. It has a context window of 200,000 tokens and a maximum output of 131,072 tokens. It accepts and returns text. It supports reasoning mode and tool calling. The weights are open. Pricing starts at $0.45 per million input tokens and $2.15 per million output tokens, with cached input at $0.08 per million tokens. It is served by 48 hosts.

Against GLM-5V-Turbo: input $0.7042 to $0.45, output $3.10 to $2.15, cached input $0.169 to $0.08.

Range across the hosts that serve it: up to $1.76 per 1M input tokens.

• ·200k token context window
• ·131k token max output
• ·Open weights for self-hosting
• ·Reasoning mode for complex tasks
• ·Tool calling for agentic workflows

• Reach for it for agentic engineering tasks
• Reach for it for terminal-based development
• Reach for it for repository generation

48 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 200,000 tokens and the maximum output is 131,072 tokens.

Does it support tool calling and reasoning?

Yes, it supports both reasoning mode and tool calling.

Is the model open weights?

Yes, the weights are open. It is served by 48 hosts.