zhipu/glm-5.3
GLM-5.3 supports text input, up to 1M tokens of context and 128K output, tool calling, structured output, and context caching. Reasoning is always enabled, with low, high, and max effort levels (max by default). thinking.type=disabled is not supported.
來源：official_2026_10_x0.70 · 核驗於 2026-10-14
快取讀取 $0.182/M · 快取寫入 —/M
API 呼叫時用任一 ID 都可以。
zhipu/glm-5.3把 ONEHOP_KEY 佔位符替換為你的 API Key。 建立 →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="zhipu/glm-5.3",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)最近 30 天 6 次請求