GLM-5 Turbo 是 GLM-5 系列的延遲最佳化版本。它保留了該系列強大的工具使用和雙語能力,同時縮短了首個 token 的生成時間,非常適合即時助手和互動功能。
可直接取代 OpenAI。只需變更 base_url 和 model。
# Python - pip install openai from openai import OpenAI client = OpenAI( base_url="https://meshtok.com/v1", api_key="sk-your-MeshTok-key", ) resp = client.chat.completions.create( model="bigmodel/glm-5-turbo", messages=[{"role":"user","content":"Hello!"}], ) print(resp.choices[0].message.content)
# cURL curl https://meshtok.com/v1/chat/completions \ -H "Authorization: Bearer sk-your-MeshTok-key" \ -H "Content-Type: application/json" \ -d '{"model":"bigmodel/glm-5-turbo","messages":[{"role":"user","content":"Hello!"}]}'
其他您可能考慮的模型。
Bilingual CN/EN embeddings from Zhipu AI.
Zhipu’s flagship with a 1M context window.
Balanced daily-driver from Zhipu.
General-purpose chat model.