15 models is the headline. The features are why you stay.

#api #ai #openai #llm

Here's everything that works out of the box — OpenAI-compatible, all of it.

Streaming

from openai import OpenAI
client = OpenAI(api_key="mb-xxx", base_url="https://aibridge-api.com/v1")

stream = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role":"user","content":"Write a haiku"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Tokens arrive as they're generated. First byte in milliseconds.
Works on all 15 models.

Function calling

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}},
    },
}]
client.chat.completions.create(
    model="qwen-max",
    messages=[{"role":"user","content":"What's the weather in Tokyo?"}],
    tools=tools,
)

Your model calls your functions. Structured arguments. No parsing
hacks.

JSON mode

client.chat.completions.create(
    model="glm-4-plus",
    messages=[{"role":"user","content":"Return a list of 5 cities as JSON"}],
    response_format={"type": "json_object"},
)

Valid JSON, guaranteed. Drop it straight into your pipeline.