OpenAI Agents (gateway)

Route LLM calls through the Respan gateway to use 250+ models from different providers. Only your Respan API key is needed — no separate provider keys required.

Setup

Install packages

$ pip install respan-ai respan-instrumentation-openai-agents

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Point to the Respan gateway

1 import os
2 import asyncio
3 from openai import AsyncOpenAI
4 from agents import Agent, Runner, set_default_openai_client
5 
6 client = AsyncOpenAI(
7     api_key=os.getenv("RESPAN_API_KEY"),
8     base_url="https://api.respan.ai/api",
9 )
10 set_default_openai_client(client)
11 
12 agent = Agent(
13     name="Assistant",
14     instructions="You only respond in haikus.",
15 )
16 
17 async def main():
18     result = await Runner.run(agent, "Tell me about recursion.")
19     print(result.final_output)
20 
21 asyncio.run(main())

Switch models

Change the model parameter on any agent to use 250+ models from different providers through the same gateway.

1 agent = Agent(
2     name="Assistant",
3     model="claude-sonnet-4-5-20250929",  # Use Anthropic via gateway
4     instructions="You are a helpful assistant.",
5 )

See the full model list.

1	import os
2	import asyncio
3	from openai import AsyncOpenAI
4	from agents import Agent, Runner, set_default_openai_client
5
6	client = AsyncOpenAI(
7	api_key=os.getenv("RESPAN_API_KEY"),
8	base_url="https://api.respan.ai/api",
9	)
10	set_default_openai_client(client)
11
12	agent = Agent(
13	name="Assistant",
14	instructions="You only respond in haikus.",
15	)
16
17	async def main():
18	result = await Runner.run(agent, "Tell me about recursion.")
19	print(result.final_output)
20
21	asyncio.run(main())

1	agent = Agent(
2	name="Assistant",
3	model="claude-sonnet-4-5-20250929", # Use Anthropic via gateway
4	instructions="You are a helpful assistant.",
5	)