GLM-5.2

GLM-5.2 is an open flagship model from Z.ai for long-horizon coding agents and million-token context work. It is the successor to GLM-5.1 in the GLM line. It has a context window of 1,000,000 tokens and a maximum output of 131,072 tokens. Weights are open. It supports reasoning mode and tool calling. It accepts text and returns text. Pricing starts at $0.088 per million input tokens and $1.05 per million output tokens, with cached input at $0.05 per million tokens.

Against GLM-5.1: window 200K to 1M, input $0.45 to $0.152, output $2.15 to $1.05, cached input $0.08 to $0.05.

Range across the hosts that serve it: up to $2.80 per 1M input tokens.

• ·1M token context window for long-horizon tasks
• ·131K token output limit
• ·Open weights for self-hosting
• ·Reasoning mode for complex coding
• ·Tool calling for agent workflows

• Reach for it for long-horizon coding agents
• Reach for it for million-token context work
• Reach for it for tasks needing tool calling
• Reach for it for self-hosted deployments

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

• 7Reflection debuts Beam, an open-weight AI model to rival Chinese models at lower compute cost2026-10-06
• 9Laptop Runs 700B-Parameter GLM! No GPU Needed? SSD as VRAM Goes Viral on GitHub2026-09-27

2 signals of the archive mention this model, each scored against the published bar. This list is rebuilt from the archive at every build, so it cannot go stale.

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

How does GLM-5.2 compare to GLM-5.1?

GLM-5.2 has a 1M token context window, up from 200k in GLM-5.1, and was released later.

Does it support tool calling?

Yes, GLM-5.2 supports tool calling and also has a reasoning mode.

What is the maximum output length?

The maximum output is 131,072 tokens.