Skip to content

OrcaRouter

OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint.

The OpenAI provider is an optional dependency. To install, run:

Terminal window
pip install 'strands-agents[openai]'

Create an API key, export it as ORCAROUTER_API_KEY, and point the provider at OrcaRouter’s endpoint:

import os
from strands import Agent
from strands.models.openai import OpenAIModel
model = OpenAIModel(
client_args={
"api_key": os.environ["ORCAROUTER_API_KEY"],
"base_url": "https://api.orcarouter.ai/v1",
},
model_id="orcarouter/auto",
)
agent = Agent(model=model)
response = agent("Explain tool calling in one sentence.")
print(response)

Two client settings connect the provider to OrcaRouter:

Model IDs come from the OrcaRouter model catalog and are prefixed with the gateway name, for example orcarouter/auto or orcarouter/fusion. For model parameters and other provider options, see the OpenAI provider guide.