Call Unquant from Python and JavaScript with the OpenAI SDK

Python

pip install openai

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.unquant.io/v1", api_key=os.environ["UNQUANT_API_KEY"])

reply = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Write a noir opening line."}],
)
print(reply.choices[0].message.content)

JavaScript and TypeScript

npm install openai

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.unquant.io/v1", apiKey: process.env.UNQUANT_API_KEY });

const reply = await client.chat.completions.create({
  model: "qwen-3.8-flash-next",
  messages: [{ role: "user", content: "Summarise this chapter in three lines." }],
});
console.log(reply.choices[0].message.content);

Streaming

stream = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Tell me a long story."}],
    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)

include_usage adds a final chunk with token counts. Usage is never billed; it is there for your own monitoring.

Images

Send images inline as base64 data URLs (PNG, JPEG or WebP). Remote image URLs are not fetched.

import base64
data = base64.b64encode(open("photo.jpg", "rb").read()).decode()
client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "What is in this picture?"},
        {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{data}"}},
    ]}],
)

Tool calling

tools = [{"type": "function", "function": {
    "name": "get_weather",
    "description": "Current weather for a city",
    "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]},
}}]
reply = client.chat.completions.create(model="glm-5.3-flash", tools=tools,
    messages=[{"role": "user", "content": "Weather in Lisbon?"}])
print(reply.choices[0].message.tool_calls)

Reasoning control

Both models reason before answering and return their thinking in reasoning_content, separate from the answer. Pass reasoning_effort as none, low or high (GLM-5.3-Flash also takes max):

client.chat.completions.create(model="glm-5.3-flash", reasoning_effort="none",
    messages=[{"role": "user", "content": "Quick answer: capital of Peru?"}])

Handling errors

The full list is in the error reference.