OpenAI compatibility

Teepin's chat API follows OpenAI's, so OpenAI's SDKs and tools built on them work by changing two settings:

from openai import OpenAI

openai = OpenAI(base_url="https://api.teepin.com/v1", api_key="tpk_...")
reply = openai.chat.completions.create(
    model="teepin/glm-5.3",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(reply.choices[0].message.content)

What is supportedCopy Anchor Link

• GET /v1/models and POST /v1/chat/completions, answered whole or streamed.
• The request fields listed on Chat completions. Others are ignored.

Embeddings, images, audio endpoints, files, fine-tuning jobs and assistants are not part of the API today.

Why use Teepin's SDKsCopy Anchor Link

OpenAI's SDKs work, and Teepin's add a few things on top:

• the attestation result for confidential models on every answer;
• retries that never bill twice: a chat request is retried only when it certainly was not billed;
• typed errors, such as no credit, rate limited and model not found.