GLM-5.3

GLM-5.3 is the flagship GLM model from Z.ai (Zhipu, GLM) for long-horizon coding, agents, and complex project delivery. It is the latest in the GLM line, succeeding GLM-5.2, which was released on 2026-06-13 with the same 1,000,000 token context window and an input price of $0.088 per million tokens. GLM-5.3 has a 1,000,000 token context window and a 131,072 token output limit. Pricing starts at $0.07 per million input tokens and $1.40 per million output tokens, with cached input at $0.06 per million tokens. Weights are open. It supports reasoning mode and tool calling, and accepts and returns text.

Against GLM-5.2: input $0.152 to $0.07, output $1.05 to $1.40, cached input $0.05 to $0.06.

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

• ·1,000,000 token context window
• ·131,072 token max output
• ·Open weights
• ·Reasoning mode and tool calling
• ·Input price from $0.07 per million

• Reach for it for long-horizon coding tasks
• Reach for it for building autonomous agents
• Reach for it for complex project delivery
• Reach for it for tasks needing 1M token context

58 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?

The context window is 1,000,000 tokens.

Are the weights open?

Yes, the weights are open.

What is the pricing?

Input from $0.07 per million tokens, output $1.40 per million, cached input $0.06 per million.