Use Modellix LLM with the OpenAI Agents SDK

Use the OpenAI Agents SDK against the Modellix LLM gateway. The SDK accepts a custom OpenAI client (base_url + API key), so you can run agents on Chat Completions at POST /v1/chat/completions — the same gateway shape as the OpenAI SDK.

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 to the model layer. Prefer OpenAIChatCompletionsModel (or MultiProvider with openai_prefix_mode="model_id") so the SDK does not strip the openai/ prefix before calling Modellix. See Models & Pricing.

Set Up the Agents SDK

Install the SDK

Python:

pip install openai-agents

TypeScript:

npm install @openai/agents openai

Set Credentials

Create a Modellix API key in the console:

export OPENAI_API_KEY="mdlx-xxxxxxxx"
export OPENAI_BASE_URL="https://llm.modellix.ai/v1"

Setting	Value
`OPENAI_API_KEY`	Modellix API Key (not an OpenAI platform key)
`OPENAI_BASE_URL`	`https://llm.modellix.ai/v1` (include `/v1`)
Model	Exact Modellix Model ID (`provider/name`)

OpenAI Tracing exports to OpenAI’s platform. A Modellix key cannot upload traces. Disable tracing, or keep model traffic on Modellix and set a separate OpenAI tracing key.

Create a Client and Agent (Recommended)

Build an AsyncOpenAI / OpenAI client pointed at Modellix, wrap it in OpenAIChatCompletionsModel with a literal Modellix Model ID, and disable tracing unless you have a separate OpenAI tracing key.

import asyncio
from openai import AsyncOpenAI
from agents import (
    Agent,
    OpenAIChatCompletionsModel,
    Runner,
    set_tracing_disabled,
)

set_tracing_disabled(True)

client = AsyncOpenAI(
    base_url="https://llm.modellix.ai/v1",
    api_key="mdlx-xxxxxxxx",  # or rely on OPENAI_API_KEY
)

agent = Agent(
    name="Assistant",
    instructions="You are a concise coding assistant.",
    model=OpenAIChatCompletionsModel(
        model="openai/gpt-5.5",
        openai_client=client,
    ),
)

async def main() -> None:
    result = await Runner.run(agent, "Say hello in one short sentence.")
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())

import { OpenAI } from "openai";
import {
  Agent,
  OpenAIChatCompletionsModel,
  Runner,
  setTracingDisabled,
} from "@openai/agents";

setTracingDisabled(true);

const client = new OpenAI({
  baseURL: "https://llm.modellix.ai/v1",
  apiKey: process.env.OPENAI_API_KEY ?? "mdlx-xxxxxxxx",
});

const agent = new Agent({
  name: "Assistant",
  instructions: "You are a concise coding assistant.",
  model: new OpenAIChatCompletionsModel(client, "openai/gpt-5.5"),
});

const result = await Runner.run(agent, "Say hello in one short sentence.");
console.log(result.finalOutput);

Change the model string 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.

Optional: Global Default Client

To make Modellix the process-wide default without wrapping every agent:

from openai import AsyncOpenAI
from agents import (
    set_default_openai_api,
    set_default_openai_client,
    set_tracing_disabled,
)

set_tracing_disabled(True)
set_default_openai_api("chat_completions")
set_default_openai_client(
    AsyncOpenAI(
        base_url="https://llm.modellix.ai/v1",
        api_key="mdlx-xxxxxxxx",
    ),
    use_for_tracing=False,
)

import { OpenAI } from "openai";
import {
  setDefaultOpenAIClient,
  setOpenAIAPI,
  setTracingDisabled,
} from "@openai/agents";

setTracingDisabled(true);
setOpenAIAPI("chat_completions");
setDefaultOpenAIClient(
  new OpenAI({
    baseURL: "https://llm.modellix.ai/v1",
    apiKey: process.env.OPENAI_API_KEY ?? "mdlx-xxxxxxxx",
  }),
);

Then assign models carefully. String IDs like openai/gpt-5.5 can be rewritten by the default OpenAI provider (it may drop the openai/ prefix). Prefer OpenAIChatCompletionsModel with the full Modellix ID, or a MultiProvider with openai_prefix_mode="model_id" (Python) so the gateway receives openai/gpt-5.5 unchanged. See Agents SDK models.

Optional: Responses API

Modellix also exposes POST /v1/responses. The SDK defaults to Responses for OpenAI-hosted traffic. On a compatible gateway, start with Chat Completions (set_default_openai_api("chat_completions") / setOpenAIAPI("chat_completions")) unless you have verified Responses + tools for your agent loop.Keep base_url as https://llm.modellix.ai/v1 for both shapes. Do not use the Anthropic host without /v1 here — that path is for the Anthropic SDK and Claude Code.

Troubleshooting

Symptom	Check
401 / auth errors	Key is a valid Modellix API key
Model not found / 404	Full ID like `openai/gpt-5.5` reaches Modellix; avoid provider prefix stripping
Wrong path	`base_url` is `https://llm.modellix.ai/v1` (include `/v1`)
Tracing / export errors	`set_tracing_disabled(True)` or a separate OpenAI tracing key with `use_for_tracing=False`
Tools / Responses failures	Switch to Chat Completions (`OpenAIChatCompletionsModel` or `chat_completions` default API)

OpenAI Agents SDK — Models — custom clients and Chat Completions
OpenAI Agents SDK — Configuration — OPENAI_BASE_URL, tracing, API shape
OpenAI platform — Agents models — model selection overview
OpenAI SDK — same /v1 gateway without the Agents runtime
LangChain — another Chat Completions client path
Models & Pricing — Model IDs and rates
LLM API guide — protocols and curl examples

Get Started

API

Agent

SDK

Framework

IDE

Tool

Use Modellix LLM with the OpenAI Agents SDK

Set Up the Agents SDK

Troubleshooting

​Set Up the Agents SDK

​Troubleshooting

​Related

Set Up the Agents SDK

Troubleshooting

Related