Strands Agents (gateway)

Route Strands Agents’ underlying LLM calls through the Respan gateway to use 250+ models from different providers. Only your RESPAN_API_KEY is needed for the gateway request path; no separate provider credentials are required in the client.

Setup

$
pip install respan-ai respan-instrumentation-strands-agents "strands-agents[openai]"

$
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

1
import os
2
from strands import Agent
3
from strands.models.openai import OpenAIModel
4
5
model = OpenAIModel(
6
    model_id="gpt-4.1-nano",
7
    client_args={
8
        "api_key": os.environ["RESPAN_API_KEY"],
9
        "base_url": "https://api.respan.ai/api",
10
    },
11
)
12
13
agent = Agent(model=model)
14
print(agent("What is the capital of France?"))

Switch models

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

1
OpenAIModel(model_id="claude-sonnet-4-5-20250929", client_args={"api_key": ..., "base_url": "https://api.respan.ai/api"})
2
OpenAIModel(model_id="gemini-2.5-flash", client_args={"api_key": ..., "base_url": "https://api.respan.ai/api"})

See the full model list.