Inference API Quickstart

pip install openai

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("TELNYX_API_KEY"),
  base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
  messages=[
    {"role": "user", "content": "Tell me about Telnyx"}
  ],
  model="zai-org/GLM-5.2",
  stream=True
)

# GLM-5.2 is a reasoning model: it streams its thinking in `reasoning_content`
# before the final answer in `content`. Print both so you can see the reasoning.
reasoning_started = False
content_started = False
for chunk in chat_completion:
  delta = chunk.choices[0].delta
  if getattr(delta, "reasoning_content", None):
    if not reasoning_started:
      print("--- reasoning ---")
      reasoning_started = True
    print(delta.reasoning_content, end="", flush=True)
  if delta.content:
    if not content_started:
      print("\n--- answer ---")
      content_started = True
    print(delta.content, end="", flush=True)