Agno (gateway)

Route Agno’s underlying OpenAI-compatible LLM calls through the Respan gateway to use 250+ models from different providers. Only your Respan API key is needed when provider access is configured in Respan.

Setup

Install packages

$ pip install agno openai

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export RESPAN_BASE_URL="https://api.respan.ai/api"

No OPENAI_API_KEY is needed when the request is routed through the Respan gateway.

Point Agno to the Respan gateway

1 import os
2 
3 from agno.agent import Agent
4 from agno.models.openai import OpenAIChat
5 
6 respan_api_key = os.environ["RESPAN_API_KEY"]
7 respan_base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")
8 
9 agent = Agent(
10     name="Gateway Agent",
11     model=OpenAIChat(
12         id="gpt-5-mini",
13         api_key=respan_api_key,
14         base_url=respan_base_url,
15     ),
16     instructions="Keep the answer short and concrete.",
17 )
18 
19 result = agent.run("Name two practical uses for distributed tracing.")
20 print(result.content)

Switch models

Change the id passed to OpenAIChat to use another OpenAI model through the same gateway-backed endpoint.

1 agent = Agent(
2     model=OpenAIChat(
3         id="gpt-5.5",
4         api_key=os.environ["RESPAN_API_KEY"],
5         base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
6     ),
7 )

OpenAIChat is Agno’s OpenAI-compatible adapter. This page avoids showing Claude or Gemini inside that OpenAI-named adapter; use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

See the full model list.