# OpenAI Agents SDK

URL: https://docs.hanzo.ai/docs/guides/integrations/openai-agents

> base_url goes on an AsyncOpenAI client. The SDK defaults to Responses, so choose the endpoint deliberately.

The base URL goes on an `AsyncOpenAI` client, parameter **`base\_url`**, which is then handed to the SDK. Three scopes take it: `set\_default\_openai\_client`globally, a`ModelProvider`through`RunConfig`per run, or`Agent.model\` per agent.

```bash
pip install openai-agents
```

```python
from agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel, set_tracing_disabled

set_tracing_disabled(disabled=True)

client = AsyncOpenAI(api_key="sk-...", base_url="https://api.hanzo.ai/v1")
model = OpenAIChatCompletionsModel(model="zen6", openai_client=client)

agent = Agent(name="Assistant", instructions="Answer precisely.", model=model)
result = Runner.run_sync(agent, "Hello")
print(result.final_output)
```

Lands on `POST /v1/chat/completions`.

The SDK's own default is the Responses API, so a plain agent would reach `POST /v1/responses` instead. Both are served, so either works — the snippet uses `OpenAIChatCompletionsModel` to make the choice visible. The other documented way to make it is `set_default_openai_api("chat_completions")`, which applies when the address and key come from `OPENAI_BASE_URL` and `OPENAI_API_KEY`.

Tracing uploads to OpenAI. With no platform.openai.com key in the environment, disable it as above or every run logs a tracing failure.

`MultiProvider(openai_base_url=..., openai_api_key=..., openai_prefix_mode="model_id", unknown_prefix_mode="model_id")` is the route for prefix-based dispatch where the endpoint expects literal namespaced ids.

## MCP

```python
from agents import Agent
from agents.mcp import MCPServerStreamableHttp

server = MCPServerStreamableHttp(params={
    "url": "https://api.hanzo.ai/v1/mcp",
    "headers": {"Authorization": "Bearer sk-..."},
    "timeout": 10,
})

agent = Agent(name="Assistant", instructions="Answer precisely.", model=model, mcp_servers=[server])
```

There is also `HostedMCPTool`, which passes a `server_url` in `tool_config` — that round trip is run by the OpenAI Responses API, not by your process.