GatewayAgent Frameworks

Smolagents (gateway)

Route Smolagents’ underlying LLM calls through the Respan gateway to use 1000+ models from different providers. Only your RESPAN_API_KEY is needed — no separate provider keys required.

Setup

1

Install packages

pip install smolagents litellm
2

Set environment variables

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

3

Point Smolagents to the Respan gateway

import os
from smolagents import CodeAgent, LiteLLMModel
model = LiteLLMModel(
    model_id="openai/gpt-5.5",
    api_key=os.environ["RESPAN_API_KEY"],
    api_base="https://api.respan.ai/api",
)
agent = CodeAgent(tools=[], model=model)
print(agent.run("What is the capital of France?"))

Switch models

Use another OpenAI model ID through the same gateway-backed LiteLLM model wrapper.

LiteLLMModel(model_id="openai/gpt-5.5", api_key=..., api_base="https://api.respan.ai/api")
LiteLLMModel(model_id="openai/gpt-5-mini", api_key=..., api_base="https://api.respan.ai/api")

Smolagents uses LiteLLM provider namespaces. This page avoids showing Claude or Gemini behind an openai/ prefix; use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

See the full model list.