---
id: "z-ai/glm-4.5"
also: ["z-ai/glm-4.5", "zai-org/GLM-4.5", "hf/zai-org/GLM-4.5", "requesty/zai/glm-4.5", "vercel/zai/glm-4.5"]
card_usd_per_m: "0.6 in, 2.2 out, at z-ai/fp8"
cheapest_list_usd_per_m: "0.6 in, 2.2 out, at z-ai/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.328 in, 2.2 out, at zai on requesty"
context: 131072
max_output: 98304
input: ["text"]
output: ["text"]
released: "2025-07-25"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 5
gateways: "requesty (2), hf (1), openrouter (1), vercel (1)"
no_training: 3
trains: 0
retains_prompts: 0
---
# Z.ai: GLM 4.5

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.