---
id: "z-ai/glm-5"
also: ["z-ai/glm-5-20260211", "zai-org/GLM-5", "hf/zai-org/GLM-5", "requesty/zai/glm-5", "vercel/zai/glm-5"]
card_usd_per_m: "1.0 in, 3.2 out, at z-ai/fp8"
cheapest_list_usd_per_m: "0.6 in, 2.08 out, at deepinfra on hf"
cheapest_effective_usd_per_m: "0.2835 in, 3.1995 out, at z-ai/fp8 on openrouter"
context: 204800
max_output: 131072
input: ["text"]
output: ["text"]
released: "2026-02-11"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 24
gateways: "openrouter (12), vercel (6), hf (4), requesty (2)"
no_training: 17
trains: 0
retains_prompts: 4
---
# Z.ai: GLM 5

GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from "writing code" to "building systems," it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the "frontend-heavy, logic-light" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.