GLM-5.1

by Zhipu · chat

GLM-5.1 is Zhipu's latest flagship model with improved reasoning, coding, and agent capabilities. Tiered pricing by context length (<=32K and >32K). 198K context window.

Pricing

Input: $0.771429/M tokens · Output: $3.085714/M tokens

Capabilities

Function Calling, JSON Mode, Streaming, Reasoning

Context: 198K tokens

Max output: 128K tokens

Routes: 1/1 healthy

Performance

TTFT: 1520ms · Latency: 10133ms · Throughput: 21.7 tok/s