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.
Installation
Section titled “Installation”The OpenAI provider is an optional dependency. To install, run:
pip install 'strands-agents[openai]'npm install @strands-agents/sdk openaiCreate an API key, export it as
ORCAROUTER_API_KEY, and point the provider at OrcaRouter’s endpoint:
import os
from strands import Agentfrom 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)import { Agent } from '@strands-agents/sdk'import { OpenAIModel } from '@strands-agents/sdk/models/openai'
const model = new OpenAIModel({ api: 'chat', apiKey: process.env.ORCAROUTER_API_KEY, clientConfig: { baseURL: 'https://api.orcarouter.ai/v1', }, modelId: 'orcarouter/auto',})
const agent = new Agent({ model })const response = await agent.invoke('Explain tool calling in one sentence.')console.log(response)Configuration
Section titled “Configuration”Two client settings connect the provider to OrcaRouter:
- API key: from your OrcaRouter dashboard
- Base URL:
https://api.orcarouter.ai/v1
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.