AutoGen - ScitiX

AutoGen is Microsoft’s framework for building multi-agent AI applications. Its OpenAIChatCompletionClient accepts a custom base_url, so agents can run on the ScitiX Model Inference API. Default model here is glm-5.2; see the Models page for the full list and pricing.

Configure

Create an API key on the ScitiX API Keys page and export it:

export SCITIX_API_KEY="<Your API Key>"

Install autogen-agentchat and autogen-ext[openai], then build a client pointed at ScitiX. Use OpenAIChatCompletionClient from autogen-ext[openai]; pass this client to an AssistantAgent to drive multi-agent teams on ScitiX.

import os
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelInfo

client = OpenAIChatCompletionClient(
    model="glm-5.2",
    base_url="https://api.scitix.ai/model-api/v1",
    api_key=os.environ["SCITIX_API_KEY"],
    model_info=ModelInfo(
        vision=False, function_calling=True, json_output=True,
        family="unknown", structured_output=True,
    ),
)

Field	Description
`model`	ScitiX model ID, e.g. `glm-5.2`
`base_url`	ScitiX OpenAI-compatible endpoint: `https://api.scitix.ai/model-api/v1`
`api_key`	Your ScitiX API key, read from the environment
`model_info`	Required for a custom model. Declare its capabilities, such as `function_calling`.

For a custom model, model_info is required. Without it, the client raises model_info is required. For a tool-calling model such as glm-5.2, set function_calling=True.

Verify

Send a message — a normal reply confirms the connection (verified on autogen-agentchat 0.7.5):

import asyncio
from autogen_core.models import UserMessage

async def main():
    r = await client.create(
        [UserMessage(content="In one short sentence, which model are you?", source="user")]
    )
    print(r.content)

asyncio.run(main())
# → I'm GLM, a large language model developed by Z.ai.