---
id: "z-ai/glm-5.2"
also: ["z-ai/glm-5.2-20260616", "zai-org/GLM-5.2", "hf/zai-org/GLM-5.2", "requesty/deepinfra/glm-5.2", "requesty/zai/glm-5.2", "vercel/zai/glm-5.2"]
card_usd_per_m: "1.4 in, 4.4 out, at z-ai/fp8"
cheapest_list_usd_per_m: "0.0066 in, 7.9833 out, at relace/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.0062 in, 6.7996 out, at wafer/us on openrouter"
context: 1048576
max_output: 943718
input: ["text"]
output: ["text"]
released: "2026-06-16"
reasoning: ["xhigh", "high", "none"]
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", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 99
gateways: "openrouter (53), vercel (25), requesty (13), hf (8)"
no_training: 78
trains: 6
retains_prompts: 23
coding: 68.8000
agentic: 38.4000
---
# Z.ai: GLM 5.2

GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**.