Smolagents (gateway)

Route Smolagents’ underlying 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

$
pip install respan-ai respan-instrumentation-smolagents

$
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

1
import os
2
from smolagents import CodeAgent, LiteLLMModel
3
4
model = LiteLLMModel(
5
    model_id="openai/gpt-4.1-nano",
6
    api_key=os.environ["RESPAN_API_KEY"],
7
    api_base="https://api.respan.ai/api",
8
)
9
10
agent = CodeAgent(tools=[], model=model)
11
print(agent.run("What is the capital of France?"))

Switch models

Change the model_id parameter on LiteLLMModel to use 250+ models from different providers through the same gateway.

1
LiteLLMModel(model_id="openai/claude-sonnet-4-5-20250929", api_key=..., api_base="https://api.respan.ai/api")
2
LiteLLMModel(model_id="openai/gemini-2.5-flash", api_key=..., api_base="https://api.respan.ai/api")

See the full model list.