Skip to main content

AI Gateway

Route your LLM calls through the AI Gateway with a single base URL change. Zero vendor lock-in: always run on the best model at the lowest cost for your use case.

​
AI Gateway

​
Overview

LlamaIndex Agents is an agentic framework built on top of LlamaIndex that enables LLMs to reason, use tools, and execute multi-step workflows. By connecting LlamaIndex Agents to Orq.ai’s AI Gateway, you get production-ready agents with enterprise-grade capabilities without changing your existing code.

​
Key Benefits

Orq.ai’s AI Gateway enhances your LlamaIndex Agents with:

Complete Observability

Track every agent step, tool use, and reasoning trace with detailed analytics

Built-in Reliability

Automatic fallbacks, retries, and load balancing for production resilience

Cost Optimization

Real-time cost tracking and spend management across all your AI operations

Multi-Provider Access

Access 300+ LLMs and 20+ providers through a single, unified integration

​
Prerequisites

Before integrating LlamaIndex Agents with Orq.ai, ensure you have:
  • An Orq.ai account and API Key
  • Python 3.9 or higher
  • LlamaIndex installed in your project
To setup your API key, see API keys & Endpoints.

​
Installation

Install LlamaIndex and required dependencies: 
pip install llama-index llama-index-llms-openai-like

​
Configuration

Configure LlamaIndex Agents to use Orq.ai’s AI Gateway with the OpenAILike class:
Python
from llama_index.llms.openai_like import OpenAILike
import os

# Configure OpenAI-compatible LLM with Orq.ai AI Gateway
llm = OpenAILike(
    model="gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    api_base="https://api.orq.ai/v3/router",
    is_chat_model=True,
)
api_base: https://api.orq.ai/v3/router

​
Basic Agent Example

Here’s a complete example using ReActAgent with a simple tool:
Python
import asyncio
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai_like import OpenAILike
import os

# Configure LLM with Orq.ai AI Gateway
llm = OpenAILike(
    model="gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    api_base="https://api.orq.ai/v3/router",
    is_chat_model=True,
)

# Define a tool
def get_weather(location: str) -> str:
    """Get the current weather for a location."""
    return f"The weather in {location} is sunny and 72°F"

# Create agent
agent = ReActAgent(
    tools=[FunctionTool.from_defaults(get_weather)],
    llm=llm,
)

async def main():
    response = await agent.run("What's the weather in San Francisco?")
    print(response)

asyncio.run(main())

​
Agent with Multiple Tools

Build agents with multiple tools for complex reasoning:
Python
import asyncio
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai_like import OpenAILike
import os

llm = OpenAILike(
    model="gpt-4o",
    api_key=os.getenv("ORQ_API_KEY"),
    api_base="https://api.orq.ai/v3/router",
    is_chat_model=True,
)

def add(a: int, b: int) -> int:
    """Add two integers."""
    return a + b

def multiply(a: int, b: int) -> int:
    """Multiply two integers."""
    return a * b

def get_company_info(company: str) -> str:
    """Get basic information about a company."""
    companies = {
        "openai": "OpenAI is an AI research company founded in 2015.",
        "anthropic": "Anthropic is an AI safety company founded in 2021.",
    }
    return companies.get(company.lower(), f"No information found for {company}")

agent = ReActAgent(
    tools=[
        FunctionTool.from_defaults(add),
        FunctionTool.from_defaults(multiply),
        FunctionTool.from_defaults(get_company_info),
    ],
    llm=llm,
    system_prompt="You are a helpful assistant with access to math and company information tools.",
)

async def main():
    response = await agent.run("What is 15 * 4, and tell me about Anthropic?")
    print(response)

asyncio.run(main())

​
Model Selection

With Orq.ai, you can use any supported model from 20+ providers:
Python
import asyncio
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai_like import OpenAILike
import os

def get_time(timezone: str) -> str:
    """Get the current time in a timezone."""
    return f"The current time in {timezone} is 14:30"

# Use Claude
claude_llm = OpenAILike(
    model="anthropic/claude-sonnet-4-6",
    api_key=os.getenv("ORQ_API_KEY"),
    api_base="https://api.orq.ai/v3/router",
    is_chat_model=True,
)

# Use Gemini
gemini_llm = OpenAILike(
    model="google-ai/gemini-2.5-flash",
    api_key=os.getenv("ORQ_API_KEY"),
    api_base="https://api.orq.ai/v3/router",
    is_chat_model=True,
)

agent = ReActAgent(
    tools=[FunctionTool.from_defaults(get_time)],
    llm=claude_llm,
)

async def main():
    response = await agent.run("What time is it in Tokyo?")
    print(response)

asyncio.run(main())

​
Evaluations & Experiments

Once your agents are running, use Evaluatorq to score outputs across a dataset and Experiments to compare configurations side-by-side.

Run Evaluations with Evaluatorq

Run parallel evaluations across your agents and compare results.

Run Experiments via the API

Compare agent configurations and view results in the AI Gateway activity dashboard.