curl https://api.sference.com/v1/chat/completions \
  -H "Authorization: Bearer $SFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.sference.com/v1",
    api_key=os.environ["SFERENCE_API_KEY"],
)

response = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)

stream = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Return the current weather for a city.",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

response = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=[{"role": "user", "content": "What is the weather in Ljubljana?"}],
    tools=tools,
)

tool_call = response.choices[0].message.tool_calls[0]
# Run the tool, append the assistant turn and a {"role": "tool", ...} message, call again

messages=[{
    "role": "user",
    "content": [
        {"type": "text", "text": "What is the total on this invoice?"},
        {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
    ],
}]

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "zai-org/GLM-5.3",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello!" },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 3,
    "total_tokens": 21,
    "prompt_tokens_details": { "cached_tokens": 0 }
  }
}

response = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=[{"role": "user", "content": doc}],
    service_tier="flex",   # 0.7x list, may queue up to 30 minutes
)