Quick Start

Aize accepts OpenAI-compatible chat completions. Point your SDK to https://api.aize.dev/v1 and use an exact model name from the current model list. Global and IR accounts use this same base URL.

Before making a request, sign in and create an API key. Key creation currently requires at least $5 of wallet balance. The examples below use GLM 5.3 Flash, which is in the gateway catalog and the default API model set.

Authentication

All API requests require authentication using your API key.

Headers

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Using the OpenAI SDK

The easiest way to integrate is using the official OpenAI SDKs.

Python

openai-python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.aize.dev/v1"
)

response = client.chat.completions.create(
    model="GLM 5.3 Flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! Can you help me?"}
    ]
)

print(response.choices[0].message.content)

TypeScript / JavaScript

openai-node

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.aize.dev/v1',
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'GLM 5.3 Flash',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello! Can you help me?' }
    ]
  });

  console.log(response.choices[0].message.content);
}

main();

Using the API Directly

You can use raw HTTP requests to interact with the API.

cURL Example

curl https://api.aize.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "GLM 5.3 Flash",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello! Can you help me?"
      }
    ]
  }'

Streaming Responses

We support server-side events (SSE) for real-time streaming.

Python Streaming

stream = client.chat.completions.create(
    model="GLM 5.3 Flash",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

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

cURL Streaming

curl -N https://api.aize.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "GLM 5.3 Flash",
    "stream": true,
    "messages": [{"role":"user","content":"Stream a 2-line poem"}]
  }'

Advanced Usage

JSON Mode

Force the model to output valid JSON.

const completion = await client.chat.completions.create({
  model: "GLM 5.3 Flash",
  response_format: { type: "json_object" },
  messages: [{ role: "user", content: "Give a todo list as JSON" }],
});

Function Calling (Tools)

Connect external tools and functions.

response = client.chat.completions.create(
    model="GLM 5.3 Flash",
    messages=[{"role": "user", "content": "What's the weather in SF?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather",
            "parameters": {
                "type": "object",
                "properties": {"location": {"type": "string"}}
            }
        }
    }]
)

tool_calls = response.choices[0].message.tool_calls

Vision

Analyze images using compatible models.

curl https://api.aize.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "GLM 5.3 Flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type":"text","text":"What is in this image?"},
        {"type":"image_url","image_url":{"url":"https://example.com/cat.jpg"}}
      ]
    }]
  }'

Quick Start

On this page