Skip to main content
Use Microsoft Agent Framework against the Modellix LLM gateway. Python clients accept a base_url for any OpenAI-compatible endpoint. Point that URL at Chat Completions (or Responses) on https://llm.modellix.ai/v1.
This page covers LLM text only (https://llm.modellix.ai).Modellix model IDs are provider/name (for example openai/gpt-5.5). Pass that full string as model. See Models & Pricing.Microsoft documents that third-party (non-Azure Direct) models are used at your own risk under their Product Terms. Review data sharing and compliance for your deployment.

Set Up Microsoft Agent Framework

1

Install the Framework

Python:
.NET (OpenAI integration packages; versions may be prerelease):
2

Set Credentials

Create a Modellix API key in the console:
Agent Framework does not load .env files automatically. Call load_dotenv() yourself, export variables in the shell, or pass api_key / base_url in code. Do not use the media host (https://api.modellix.ai).
3

Create an Agent with Chat Completions (Recommended)

Use OpenAIChatCompletionClient for maximum compatibility with OpenAI-compatible gateways:
You can omit base_url / api_key in the constructor when OPENAI_BASE_URL and OPENAI_API_KEY are set in the environment.Change model to any catalog ID (anthropic/claude-sonnet-5, google/gemini-3.6-flash, and so on). Traffic still uses Chat Completions on https://llm.modellix.ai/v1.
4

Optional: Responses Client

Modellix also exposes POST /v1/responses. Use OpenAIChatClient when you want the Responses path:
Prefer Chat Completions first if tools or streaming behave unexpectedly on Responses through a gateway.
5

Optional: .NET

Point the OpenAI .NET client at Modellix, then create an agent:
Keep Endpoint as https://llm.modellix.ai/v1 and use a full Modellix Model ID.

Troubleshooting